[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72TGYZAZBCQ47TNVFS75QE2":3,"skill-same:01M72TGYZAZBCQ47TNVFS75QE2":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M72TGYZAZBCQ47TNVFS75QE2","ywc-confidence-gate",null,"(ywc) Use when checking readiness before non-trivial implementation, executor\u002Fcode-gen delegation, or a design path with material rework cost. Triggers: \"confidence check\", \"confidence gate\", \"ready to implement\", \"should I proceed\", \"준비 됐어\", \"구현 시작해도 돼\", \"実装着手\", \"確信度チェック\", \"ywc-confidence-gate\". Do not use for completion verification (use ywc-verify-done), spec quality review (use ywc-spec-validate), implementation review (use ywc-impl-review), or brainstorming intent (use ywc-brainstorm).","yongwoon\u002Fywc-agent-toolkit","yongwoon","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9317029?v=4","01M72SZSF6VKANKG5QTMV4V95S","01M72SZSG8HHC3W2CV5P7EJ5AH",8,"MIT","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: ywc-confidence-gate\ndescription: >-\n  (ywc) Use when checking readiness before non-trivial implementation,\n  executor\u002Fcode-gen delegation, or a design path with material rework cost.\n  Triggers: \"confidence check\", \"confidence gate\", \"ready to implement\",\n  \"should I proceed\", \"준비 됐어\", \"구현 시작해도 돼\", \"実装着手\",\n  \"確信度チェック\", \"ywc-confidence-gate\". Do not use for completion\n  verification (use ywc-verify-done), spec quality review (use\n  ywc-spec-validate), implementation review (use ywc-impl-review), or\n  brainstorming intent (use ywc-brainstorm).\n---\n\n# ywc-confidence-gate\n\n**Announce at start:** \"I'm using the ywc-confidence-gate skill to score readiness across five dimensions before implementation begins.\"\n\nThis skill is the canonical pre-implementation gate. It exists because every implementation skill (`ywc-code-gen`, `ywc-sequential-executor`, `ywc-parallel-executor`) starts producing code immediately when invoked — and the cost of code produced from a half-understood spec is borne later by `ywc-impl-review`, CI, or production. A 5-minute confidence score catches the same defect classes that a 30-minute re-plan and a 2-hour debug session would catch — at a fraction of the cost.\n\nThe scoring rubric and band definitions are shared with `ywc-impl-review` and other downstream skills via [`..\u002Freferences\u002Fconfidence-gate.md`](..\u002Freferences\u002Fconfidence-gate.md). This skill does not redefine the rubric; it applies it at the pre-implementation entry point.\n\n## The Iron Law\n\n```text\nNO IMPLEMENTATION WITHOUT AN EXPLICIT CONFIDENCE SCORE AND BAND DECISION\n```\n\nIf the aggregate score is below 90 and the band is REVIEW or STOP, implementation does **not** begin until the weakest dimension has been raised (or the user has explicitly accepted the residual risk and the agent has surfaced what cannot be raised). \"I'll figure it out as I go\" is not a band decision — it is the failure mode this skill exists to prevent.\n\n## Rationalization Defense\n\nWhen tempted to skip the gate, check this table first:\n\n| Excuse | Reality |\n|---|---|\n| \"The user already approved the spec, that means PROCEED\" | Spec approval is one signal among five (Scope clarity). Architecture compliance, evidence quality, reuse, and root cause are independent — a spec can be perfectly clear and still rest on an unverified architectural assumption. Score all five before deciding. |\n| \"I have high confidence overall — skipping the per-dimension scoring is fine\" | \"Overall\" confidence is the failure mode. The point of the rubric is to surface the **weakest** dimension; aggregate-only scoring lets a strong dimension (e.g., scope clarity 95) mask a fatal weakness elsewhere (e.g., reuse verified 40 because no one searched the existing utils). The single-dim-below-50 rule is what catches these. |\n| \"Scoring is bureaucracy when the change is small\" | A 5-minute gate on a 5-line change is fast. A 2-hour debug session on the same 5-line change because no one checked if a utility already exists is slow. The gate scales **down** for small changes (most dimensions score 95+ trivially), but it must still be executed and surfaced. |\n| \"I'll score after to validate that proceeding was right\" | Scoring after the fact is rationalization, not evidence. The point is to score before the decision so the score *informs* it. Post-hoc scores always conveniently clear the threshold. |\n| \"Evidence quality dimension is hard to score precisely — I'll round up\" | \"Round up to clear the threshold\" is the most common gate-defeating move. A dimension at 65 is REVIEW; rounding to 70 to PROCEED is a documented anti-pattern in the shared rubric (§7). Score honestly; if the band is REVIEW, present alternatives — that is the correct outcome. |\n| \"REVIEW band wastes time on questions the user already has answers to\" | REVIEW band exists precisely to surface those answers explicitly so they bind the implementation. If the user has them in their head but they are not in the spec, the implementation will diverge. Present the 1–3 alternatives or open questions; the user clears them in seconds. |\n| \"STOP band is for catastrophic situations only\" | STOP fires whenever aggregate \u003C 70 *or* any required dimension \u003C 70. It is not catastrophic — it is \"the current evidence does not support starting; raise it first\". Treat STOP as \"go back to spec \u002F research \u002F context\", not as \"abandon project\". |\n| \"If I report a sub-90 band, the user will think I'm being slow\" | The opposite. Reporting a REVIEW band with the weakest dimension named saves the user the rework cycle they would otherwise pay for. The gate is a transparency mechanism — the alternative is opaque overconfidence that surfaces as broken CI hours later. |\n| \"I can skip the gate when running from inside another skill (e.g., ywc-agentic loop)\" | Skill-to-skill delegation is the **most** dangerous entry point — the upstream context narrows what is in scope, and the downstream skill may not see the spec the user actually wrote. Always re-score at the boundary; do not inherit confidence from an upstream caller. |\n| \"The five dimensions don't apply to my type of work\" | They are deliberately abstract so they apply across feature work, bug fixes, refactors, and infra. If a dimension feels not-applicable, score it generously (90+) — but score it. Removing a dimension defeats the comparability of scores across skills, which is the rubric's primary value. |\n\n**Violating the letter of this discipline is violating the spirit.** The rubric is shared with downstream skills precisely so that scores remain comparable — a score from this skill must mean the same thing as a score from `ywc-impl-review`.\n\n## The Five Dimensions\n\n> Read [`..\u002Freferences\u002Fconfidence-gate.md`](..\u002Freferences\u002Fconfidence-gate.md) for the canonical rubric definition. The summary below is for quick reference; the reference file is the authoritative source.\n\n| # | Dimension | Weight | One-sentence test |\n|---|---|---|---|\n| 1 | Scope clarity | 25% | \"Can I state in one sentence what is in scope and one sentence what is out — without using vague terms like 'related cleanup' or 'and other improvements'?\" |\n| 2 | Architecture compliance | 25% | \"Does the planned change follow existing structure \u002F naming \u002F abstractions, or am I introducing a new pattern? If new, was it discussed?\" |\n| 3 | Evidence quality | 20% | \"Are the claims I am about to act on backed by primary sources (current file content, official docs, test output) or by inference \u002F memory?\" |\n| 4 | Reuse verified | 15% | \"Have I searched the codebase \u002F package registry for existing utilities that solve this? Listed them and ruled each out with a reason?\" |\n| 5 | Root cause identified | 15% | \"For a bug fix, do I name the underlying cause (not the symptom)? For greenfield work, do I name the underlying user need (not the surface request)?\" |\n\nScore each dimension 0–100. Aggregate is the weighted sum, rounded to the nearest integer.\n\n## The Decision Bands\n\n| Band | Aggregate score | Per-dim override | Action |\n|---|---|---|---|\n| **PROCEED** | ≥ 90 | All ≥ 50 | Begin implementation. Report the score in the completion summary or the executor's per-step report. |\n| **REVIEW** | 70–89 | None \u003C 50 | Present 1–3 alternatives or open questions before proceeding. Trigger the [Advisor Pattern](..\u002Freferences\u002Fadvisor-pattern.md) for any dimension \u003C 70. Do not begin implementation until at least the weakest dimension is raised or explicitly accepted. |\n| **STOP** | \u003C 70 | Any \u003C 50 (forces this band even if aggregate ≥ 70) | Do not begin implementation. Report which dimensions are weak and what evidence would raise them. Hand back to `ywc-plan` (architecture \u002F scope), `ywc-spec-validate` (evidence), `ywc-tech-research` (reuse), or `ywc-brainstorm` (root cause \u002F user need). When the architecture dimension specifically scores below 70 and the decision is irreversible, request one bounded architecture advisor pass when the current runtime supports delegation; otherwise route back to `ywc-plan` with the missing evidence named (see [Step 7: STOP-band Advisor Dispatch](#step-7-stop-band-advisor-dispatch)). |\n\n**Single-dim ≤ 50 rule**: even if aggregate would clear the threshold, a single dimension scoring at or below 50 drops the band by one level (PROCEED → REVIEW, REVIEW → STOP). This prevents one strong dimension from masking a fatal weakness.\n\n## Analyst contract\n\nEvery analyst packet carries `Caller: ywc-confidence-gate` and `analysis_mode=confidence_root_cause` plus bounded evidence. Missing, unknown, or mismatched caller\u002Fmode returns `NEEDS_CONTEXT` without inferring another mode. Validate the returned Status\u002FSummary\u002FFinding counts envelope and matching Analysis mode before consuming advice; owner\u002Finput\u002Foutput\u002Fstatus mismatch returns `NEEDS_CONTEXT`. An analyst refusal consumes the existing dispatch budget; preserve the caller's original gate and surface the missing evidence instead of re-dispatching or falling through. The analyst returns inline advice and never writes the caller's report or runs probes. Unavailable delegation uses the documented inline path; unavailable live runtime evidence is `UNVERIFIED — instruction contract only`.\n\n## Workflow\n\n### Step 1: Establish the work item\n\nState in one sentence what is about to be implemented. If the sentence requires three or more clauses, the work item is too large — split it via `ywc-task-generator` before continuing.\n\n### Step 2: Score each dimension explicitly\n\nFor each of the five dimensions, do **all** of the following:\n\n1. Read the one-sentence test (above).\n2. State the evidence supporting the current score in 1–2 lines — file paths, command outputs, doc references, or the absence of those.\n3. Score 0–100. Be honest; rounding up is the defeating move.\n\nUse [`references\u002Fpre-implementation-checklist.md`](references\u002Fpre-implementation-checklist.md) for the per-dimension probe questions.\n\n### Step 3: Compute the aggregate\n\n```text\naggregate = (scope × 0.25)\n          + (architecture × 0.25)\n          + (evidence × 0.20)\n          + (reuse × 0.15)\n          + (root_cause × 0.15)\n```\n\nRound to the nearest integer.\n\n### Step 4: Apply the single-dim override\n\nIf any dimension scored ≤ 50, drop the band by one level. PROCEED becomes REVIEW; REVIEW becomes STOP.\n\n### Step 5: Surface the report\n\nPrint the report in the canonical format below (this is the same shape `ywc-impl-review` uses for post-implementation confidence — by design, so scores stay comparable).\n\n### Step 6: Act on the band\n\n- **PROCEED**: invoke the implementation skill (`ywc-code-gen`, `ywc-sequential-executor`, etc.) immediately. Carry the score into the executor's per-step report.\n- **REVIEW**: present 1–3 alternatives or open questions; wait for user response or trigger the Advisor Pattern for the weakest dimension. Do not begin implementation in this turn.\n- **STOP**: surface the failing dimensions and route back to the appropriate upstream skill (see §Decision Bands above). Do not begin implementation. When the failing dimension qualifies as a Trigger condition below, run **Step 7** before handing back.\n\n### Step 7: STOP-band Advisor Dispatch\n\n**Trigger condition**: `band == STOP` AND at least one dimension among (architecture \u002F scope \u002F evidence \u002F reuse \u002F root cause) scored `\u003C 50`. STOP without a sub-50 dimension routes directly to the upstream skill listed in §Decision Bands without an advisor pass.\n\nThis step adopts the advisor dispatch pattern established by `ywc-plan` Step 3.5 (Architectural Advisor Gate) and `ywc-incident-postmortem` Step 4.5 — bounded payload, single dispatch, verdict-as-evidence, re-gate or handoff. See [`..\u002Freferences\u002Fadvisor-pattern.md`](..\u002Freferences\u002Fadvisor-pattern.md) for the canonical pattern definition.\n\n**5-step procedure**:\n\n1. **Frame the gap** — in 1–3 sentences, state the specific decision blocked by the failing dimension. \"What would I do differently with a definitive answer?\" If the answer is \"nothing\", do not dispatch.\n2. **Bounded payload** — assemble the minimal context the advisor needs: the failing dimension name + score + evidence line, the current work item one-liner from Step 1, and any spec excerpt or repo snippet directly relevant. Hard cap: **≤ 200 lines**. The payload is the gap, not the entire context.\n3. **Dispatch the advisor** — invoke the routing target from the table below. Pass the bounded payload + the framed decision. For non-root-cause advisors, expect `proceed | reconsider with refinements | needs more context`. For the root-cause analyst, require the analyst envelope and exactly one cause candidate with evidence for and against; no ranked alternatives or 5 Whys chain. Re-scoring and band decisions remain this caller's responsibility.\n4. **Record the verdict** — paste the verdict (or its summary if long) under the dimension's evidence line. The verdict becomes part of the dimension's evidence for the re-gate.\n5. **Re-run the gate or hand off** — re-score the failing dimension using the verdict as new evidence. If the dimension now ≥ 70, re-run aggregate + Step 4 override; the band may transition to REVIEW or PROCEED. If still \u003C 70, hand off to the upstream skill listed in §Decision Bands, carrying the verdict as additional context.\n\n**Routing target table** (per failing dimension):\n\n| Failing dimension | Routing target | Why |\n|---|---|---|\n| Architecture (`\u003C 50`) | Bounded architecture advisor pass when delegation is available; otherwise `ywc-plan` | Design \u002F trade-off analysis for irreversible architectural decisions |\n| Evidence (`\u003C 50`) | `ywc-spec-validate` skill | Spec quality review surfaces missing acceptance criteria \u002F contradictions before implementation |\n| Reuse (`\u003C 50`) | `ywc-tech-research` skill | Targeted research into existing utilities, packages, or implementations that may eliminate the need to build from scratch |\n| Root cause (`\u003C 50`) | One bounded root-cause analyst pass when delegation is available; otherwise a read-only inline analysis that edits nothing. Do not invoke the full `ywc-debug-rootcause` workflow here | Pass `Caller: ywc-confidence-gate` and `analysis_mode=confidence_root_cause`; receive exactly one cause candidate with evidence for and against, without ranked alternatives or a 5 Whys chain. `ywc-debug-rootcause` plans and applies fixes, so it would run before this gate re-scores; record the result, re-score per procedure step 5, and hand off through §Decision Bands if the dimension stays `\u003C 70`; invoke `ywc-debug-rootcause` only after the gate allows implementation |\n\nScope dimension `\u003C 50` does NOT have an advisor target — STOP on scope routes back to `ywc-plan` (Scale assessment) or `ywc-brainstorm` (intent surfacing) via §Decision Bands directly; an advisor cannot disambiguate scope without first knowing what the user actually wants.\n\n**Budget**: **1 advisor dispatch per gate run**. Even if multiple dimensions score `\u003C 50`, dispatch the one with the lowest absolute score (or the architecturally most foundational — architecture > root cause > evidence > reuse) and let its verdict propagate through re-scoring. Multiple dispatches in one gate run defeat the bounded-payload discipline by accumulating context across iterations.\n\n**When NOT to dispatch**:\n\n- `band == STOP` with no dimension `\u003C 50` (the STOP came purely from aggregate `\u003C 70`) — hand off to the upstream skill listed in §Decision Bands directly.\n- The framed gap has no decision-altering answer (Step 1 \"nothing would change with an answer\") — dispatch wastes a budgeted call.\n- The same dispatch already ran in the immediately preceding gate run on the same work item — accept the prior verdict as still valid and use §Decision Bands directly.\n\n## Output Format\n\n```text\nConfidence Gate Report\n──────────────────────\nAggregate: \u003CNN>\u002F100 — \u003CPROCEED | REVIEW | STOP>\n\n  Scope clarity:           \u003CNN>   \u003Cone-line evidence>\n  Architecture compliance: \u003CNN>   \u003Cone-line evidence>\n  Evidence quality:        \u003CNN>   \u003Cone-line evidence>\n  Reuse verified:          \u003CNN>   \u003Cone-line evidence>\n  Root cause identified:   \u003CNN>   \u003Cone-line evidence>\n\n\u003CIf REVIEW or STOP:>\nWeakest dimension: \u003Cname> (\u003CNN>)\nWhy: \u003Cone or two sentences explaining what is missing>\nWhat would raise it: \u003Cconcrete evidence or action — file to read, command to run, question to ask>\n\n\u003CIf REVIEW:>\nAlternatives presented for user decision:\n  A. \u003Coption> — trade-off\n  B. \u003Coption> — trade-off\n  (C. \u003Coption> — trade-off)\n\n\u003CIf STOP:>\nRouting: \u003Cywc-plan | ywc-spec-validate | ywc-tech-research | ywc-brainstorm> — \u003Cwhy>\n```\n\nThe \"Weakest dimension\" and \"What would raise it\" lines are **mandatory** whenever the band is REVIEW or STOP. They are the mechanism that turns the gate from a roadblock into a step-by-step path forward.\n\n## Integration\n\n- **Upstream callers**: user invocation; `ywc-plan` (after Scale assessment, before downstream handoff); `ywc-code-gen` (Step 0, before Reuse Gate); `ywc-sequential-executor` \u002F `ywc-parallel-executor` (before per-task implementation begins, especially for tasks with no upstream `ywc-plan` evidence); `ywc-agentic` (per-iteration entry).\n- **Downstream**: implementation skills proceed on PROCEED; user dialog or Advisor Pattern on REVIEW; `ywc-plan` \u002F `ywc-spec-validate` \u002F `ywc-tech-research` \u002F `ywc-brainstorm` on STOP.\n- **Pairs with**: `ywc-verify-done` (the symmetric **post**-implementation gate — that gates the claim, this gates the start); `ywc-impl-review` (uses the same rubric for post-review confidence — scores remain comparable across the two gates).\n\n## Validation Checklist\n\nBefore reporting a PROCEED band and beginning implementation, verify:\n\n- [ ] All five dimensions have explicit numeric scores (not \"high\", not \"OK\")\n- [ ] Each dimension has a one-line evidence statement\n- [ ] No dimension scored at or below 50\n- [ ] Aggregate was computed with the rubric weights (25\u002F25\u002F20\u002F15\u002F15)\n- [ ] The single-dim override was applied if any score ≤ 50\n- [ ] The score and band are surfaced in the response **before** any implementation tool is invoked\n- [ ] If REVIEW or STOP, no implementation skill was invoked in the same turn\n\n## Common Mistakes\n\n(Procedural failure modes specific to this skill. Behavioral rationalizations are in the table above — do not duplicate here.)\n\n- **Scoring after the implementation already started in the same turn.** The report must appear before the first implementation tool call. Scoring after invokes the gate retroactively — at which point its primary value (preventing the call) is gone.\n- **Reporting only the aggregate, not the per-dimension breakdown.** A single number hides the weakest dimension; that is exactly the information the user needs to act. Always print all five dimension scores.\n- **Carrying an upstream skill's confidence forward instead of re-scoring.** Each skill boundary re-narrows the context. A PROCEED at `ywc-plan` does not automatically transfer to `ywc-code-gen`, because the code-gen step has its own dimensions to score (especially Reuse verified and Architecture compliance, which `ywc-plan` does not score as deeply).\n- **Treating REVIEW as a soft STOP.** REVIEW is \"proceed with explicit alternatives presented and one of them chosen\". STOP is \"do not proceed\". Conflating them collapses three bands into two and defeats the rubric's resolution.\n- **Adding a sixth dimension because \"my work has a unique aspect\".** The five dimensions are fixed across skills so scores remain comparable. Per-skill adjustments belong in the \"required dimensions\" profile (see `references\u002Fconfidence-gate.md` §4), not in extra dimensions.\n\n## References\n\n| Reference | Use when |\n|---|---|\n| [..\u002Freferences\u002Fconfidence-gate.md](..\u002Freferences\u002Fconfidence-gate.md) | Authoritative rubric definition; per-skill required-dimension profiles; status mapping; anti-patterns |\n| [references\u002Fpre-implementation-checklist.md](references\u002Fpre-implementation-checklist.md) | Per-dimension probe questions specific to the pre-implementation moment (this skill's distinct usage from the post-review usage in `ywc-impl-review`) |\n| [..\u002Freferences\u002Fadvisor-pattern.md](..\u002Freferences\u002Fadvisor-pattern.md) | Escalating a weak dimension to a higher-capability advisor for a second opinion before changing the band |\n| `ywc-verify-done` | The symmetric post-implementation gate; both gates use the same rubric so the start-of-work and end-of-work scores are directly comparable |\n","# ywc-confidence-gate\n\n**Announce at start:** \"I'm using the ywc-confidence-gate skill to score readiness across five dimensions before implementation begins.\"\n\nThis skill is the canonical pre-implementation gate. It exists because every implementation skill (`ywc-code-gen`, `ywc-sequential-executor`, `ywc-parallel-executor`) starts producing code immediately when invoked — and the cost of code produced from a half-understood spec is borne later by `ywc-impl-review`, CI, or production. A 5-minute confidence score catches the same defect classes that a 30-minute re-plan and a 2-hour debug session would catch — at a fraction of the cost.\n\nThe scoring rubric and band definitions are shared with `ywc-impl-review` and other downstream skills via [`..\u002Freferences\u002Fconfidence-gate.md`](..\u002Freferences\u002Fconfidence-gate.md). This skill does not redefine the rubric; it applies it at the pre-implementation entry point.\n\n## The Iron Law\n\n```text\nNO IMPLEMENTATION WITHOUT AN EXPLICIT CONFIDENCE SCORE AND BAND DECISION\n```\n\nIf the aggregate score is below 90 and the band is REVIEW or STOP, implementation does **not** begin until the weakest dimension has been raised (or the user has explicitly accepted the residual risk and the agent has surfaced what cannot be raised). \"I'll figure it out as I go\" is not a band decision — it is the failure mode this skill exists to prevent.\n\n## Rationalization Defense\n\nWhen tempted to skip the gate, check this table first:\n\n| Excuse | Reality |\n|---|---|\n| \"The user already approved the spec, that means PROCEED\" | Spec approval is one signal among five (Scope clarity). Architecture compliance, evidence quality, reuse, and root cause are independent — a spec can be perfectly clear and still rest on an unverified architectural assumption. Score all five before deciding. |\n| \"I have high confidence overall — skipping the per-dimension scoring is fine\" | \"Overall\" confidence is the failure mode. The point of the rubric is to surface the **weakest** dimension; aggregate-only scoring lets a strong dimension (e.g., scope clarity 95) mask a fatal weakness elsewhere (e.g., reuse verified 40 because no one searched the existing utils). The single-dim-below-50 rule is what catches these. |\n| \"Scoring is bureaucracy when the change is small\" | A 5-minute gate on a 5-line change is fast. A 2-hour debug session on the same 5-line change because no one checked if a utility already exists is slow. The gate scales **down** for small changes (most dimensions score 95+ trivially), but it must still be executed and surfaced. |\n| \"I'll score after to validate that proceeding was right\" | Scoring after the fact is rationalization, not evidence. The point is to score before the decision so the score *informs* it. Post-hoc scores always conveniently clear the threshold. |\n| \"Evidence quality dimension is hard to score precisely — I'll round up\" | \"Round up to clear the threshold\" is the most common gate-defeating move. A dimension at 65 is REVIEW; rounding to 70 to PROCEED is a documented anti-pattern in the shared rubric (§7). Score honestly; if the band is REVIEW, present alternatives — that is the correct outcome. |\n| \"REVIEW band wastes time on questions the user already has answers to\" | REVIEW band exists precisely to surface those answers explicitly so they bind the implementation. If the user has them in their head but they are not in the spec, the implementation will diverge. Present the 1–3 alternatives or open questions; the user clears them in seconds. |\n| \"STOP band is for catastrophic situations only\" | STOP fires whenever aggregate \u003C 70 *or* any required dimension \u003C 70. It is not catastrophic — it is \"the current evidence does not support starting; raise it first\". Treat STOP as \"go back to spec \u002F research \u002F context\", not as \"abandon project\". |\n| \"If I report a sub-90 band, the user will think I'm being slow\" | The opposite. Reporting a REVIEW band with the weakest dimension named saves the user the rework cycle they would otherwise pay for. The gate is a transparency mechanism — the alternative is opaque overconfidence that surfaces as broken CI hours later. |\n| \"I can skip the gate when running from inside another skill (e.g., ywc-agentic loop)\" | Skill-to-skill delegation is the **most** dangerous entry point — the upstream context narrows what is in scope, and the downstream skill may not see the spec the user actually wrote. Always re-score at the boundary; do not inherit confidence from an upstream caller. |\n| \"The five dimensions don't apply to my type of work\" | They are deliberately abstract so they apply across feature work, bug fixes, refactors, and infra. If a dimension feels not-applicable, score it generously (90+) — but score it. Removing a dimension defeats the comparability of scores across skills, which is the rubric's primary value. |\n\n**Violating the letter of this discipline is violating the spirit.** The rubric is shared with downstream skills precisely so that scores remain comparable — a score from this skill must mean the same thing as a score from `ywc-impl-review`.\n\n## The Five Dimensions\n\n> Read [`..\u002Freferences\u002Fconfidence-gate.md`](..\u002Freferences\u002Fconfidence-gate.md) for the canonical rubric definition. The summary below is for quick reference; the reference file is the authoritative source.\n\n| # | Dimension | Weight | One-sentence test |\n|---|---|---|---|\n| 1 | Scope clarity | 25% | \"Can I state in one sentence what is in scope and one sentence what is out — without using vague terms like 'related cleanup' or 'and other improvements'?\" |\n| 2 | Architecture compliance | 25% | \"Does the planned change follow existing structure \u002F naming \u002F abstractions, or am I introducing a new pattern? If new, was it discussed?\" |\n| 3 | Evidence quality | 20% | \"Are the claims I am about to act on backed by primary sources (current file content, official docs, test output) or by inference \u002F memory?\" |\n| 4 | Reuse verified | 15% | \"Have I searched the codebase \u002F package registry for existing utilities that solve this? Listed them and ruled each out with a reason?\" |\n| 5 | Root cause identified | 15% | \"For a bug fix, do I name the underlying cause (not the symptom)? For greenfield work, do I name the underlying user need (not the surface request)?\" |\n\nScore each dimension 0–100. Aggregate is the weighted sum, rounded to the nearest integer.\n\n## The Decision Bands\n\n| Band | Aggregate score | Per-dim override | Action |\n|---|---|---|---|\n| **PROCEED** | ≥ 90 | All ≥ 50 | Begin implementation. Report the score in the completion summary or the executor's per-step report. |\n| **REVIEW** | 70–89 | None \u003C 50 | Present 1–3 alternatives or open questions before proceeding. Trigger the [Advisor Pattern](..\u002Freferences\u002Fadvisor-pattern.md) for any dimension \u003C 70. Do not begin implementation until at least the weakest dimension is raised or explicitly accepted. |\n| **STOP** | \u003C 70 | Any \u003C 50 (forces this band even if aggregate ≥ 70) | Do not begin implementation. Report which dimensions are weak and what evidence would raise them. Hand back to `ywc-plan` (architecture \u002F scope), `ywc-spec-validate` (evidence), `ywc-tech-research` (reuse), or `ywc-brainstorm` (root cause \u002F user need). When the architecture dimension specifically scores below 70 and the decision is irreversible, request one bounded architecture advisor pass when the current runtime supports delegation; otherwise route back to `ywc-plan` with the missing evidence named (see [Step 7: STOP-band Advisor Dispatch](#step-7-stop-band-advisor-dispatch)). |\n\n**Single-dim ≤ 50 rule**: even if aggregate would clear the threshold, a single dimension scoring at or below 50 drops the band by one level (PROCEED → REVIEW, REVIEW → STOP). This prevents one strong dimension from masking a fatal weakness.\n\n## Analyst contract\n\nEvery analyst packet carries `Caller: ywc-confidence-gate` and `analysis_mode=confidence_root_cause` plus bounded evidence. Missing, unknown, or mismatched caller\u002Fmode returns `NEEDS_CONTEXT` without inferring another mode. Validate the returned Status\u002FSummary\u002FFinding counts envelope and matching Analysis mode before consuming advice; owner\u002Finput\u002Foutput\u002Fstatus mismatch returns `NEEDS_CONTEXT`. An analyst refusal consumes the existing dispatch budget; preserve the caller's original gate and surface the missing evidence instead of re-dispatching or falling through. The analyst returns inline advice and never writes the caller's report or runs probes. Unavailable delegation uses the documented inline path; unavailable live runtime evidence is `UNVERIFIED — instruction contract only`.\n\n## Workflow\n\n### Step 1: Establish the work item\n\nState in one sentence what is about to be implemented. If the sentence requires three or more clauses, the work item is too large — split it via `ywc-task-generator` before continuing.\n\n### Step 2: Score each dimension explicitly\n\nFor each of the five dimensions, do **all** of the following:\n\n1. Read the one-sentence test (above).\n2. State the evidence supporting the current score in 1–2 lines — file paths, command outputs, doc references, or the absence of those.\n3. Score 0–100. Be honest; rounding up is the defeating move.\n\nUse [`references\u002Fpre-implementation-checklist.md`](references\u002Fpre-implementation-checklist.md) for the per-dimension probe questions.\n\n### Step 3: Compute the aggregate\n\n```text\naggregate = (scope × 0.25)\n          + (architecture × 0.25)\n          + (evidence × 0.20)\n          + (reuse × 0.15)\n          + (root_cause × 0.15)\n```\n\nRound to the nearest integer.\n\n### Step 4: Apply the single-dim override\n\nIf any dimension scored ≤ 50, drop the band by one level. PROCEED becomes REVIEW; REVIEW becomes STOP.\n\n### Step 5: Surface the report\n\nPrint the report in the canonical format below (this is the same shape `ywc-impl-review` uses for post-implementation confidence — by design, so scores stay comparable).\n\n### Step 6: Act on the band\n\n- **PROCEED**: invoke the implementation skill (`ywc-code-gen`, `ywc-sequential-executor`, etc.) immediately. Carry the score into the executor's per-step report.\n- **REVIEW**: present 1–3 alternatives or open questions; wait for user response or trigger the Advisor Pattern for the weakest dimension. Do not begin implementation in this turn.\n- **STOP**: surface the failing dimensions and route back to the appropriate upstream skill (see §Decision Bands above). Do not begin implementation. When the failing dimension qualifies as a Trigger condition below, run **Step 7** before handing back.\n\n### Step 7: STOP-band Advisor Dispatch\n\n**Trigger condition**: `band == STOP` AND at least one dimension among (architecture \u002F scope \u002F evidence \u002F reuse \u002F root cause) scored `\u003C 50`. STOP without a sub-50 dimension routes directly to the upstream skill listed in §Decision Bands without an advisor pass.\n\nThis step adopts the advisor dispatch pattern established by `ywc-plan` Step 3.5 (Architectural Advisor Gate) and `ywc-incident-postmortem` Step 4.5 — bounded payload, single dispatch, verdict-as-evidence, re-gate or handoff. See [`..\u002Freferences\u002Fadvisor-pattern.md`](..\u002Freferences\u002Fadvisor-pattern.md) for the canonical pattern definition.\n\n**5-step procedure**:\n\n1. **Frame the gap** — in 1–3 sentences, state the specific decision blocked by the failing dimension. \"What would I do differently with a definitive answer?\" If the answer is \"nothing\", do not dispatch.\n2. **Bounded payload** — assemble the minimal context the advisor needs: the failing dimension name + score + evidence line, the current work item one-liner from Step 1, and any spec excerpt or repo snippet directly relevant. Hard cap: **≤ 200 lines**. The payload is the gap, not the entire context.\n3. **Dispatch the advisor** — invoke the routing target from the table below. Pass the bounded payload + the framed decision. For non-root-cause advisors, expect `proceed | reconsider with refinements | needs more context`. For the root-cause analyst, require the analyst envelope and exactly one cause candidate with evidence for and against; no ranked alternatives or 5 Whys chain. Re-scoring and band decisions remain this caller's responsibility.\n4. **Record the verdict** — paste the verdict (or its summary if long) under the dimension's evidence line. The verdict becomes part of the dimension's evidence for the re-gate.\n5. **Re-run the gate or hand off** — re-score the failing dimension using the verdict as new evidence. If the dimension now ≥ 70, re-run aggregate + Step 4 override; the band may transition to REVIEW or PROCEED. If still \u003C 70, hand off to the upstream skill listed in §Decision Bands, carrying the verdict as additional context.\n\n**Routing target table** (per failing dimension):\n\n| Failing dimension | Routing target | Why |\n|---|---|---|\n| Architecture (`\u003C 50`) | Bounded architecture advisor pass when delegation is available; otherwise `ywc-plan` | Design \u002F trade-off analysis for irreversible architectural decisions |\n| Evidence (`\u003C 50`) | `ywc-spec-validate` skill | Spec quality review surfaces missing acceptance criteria \u002F contradictions before implementation |\n| Reuse (`\u003C 50`) | `ywc-tech-research` skill | Targeted research into existing utilities, packages, or implementations that may eliminate the need to build from scratch |\n| Root cause (`\u003C 50`) | One bounded root-cause analyst pass when delegation is available; otherwise a read-only inline analysis that edits nothing. Do not invoke the full `ywc-debug-rootcause` workflow here | Pass `Caller: ywc-confidence-gate` and `analysis_mode=confidence_root_cause`; receive exactly one cause candidate with evidence for and against, without ranked alternatives or a 5 Whys chain. `ywc-debug-rootcause` plans and applies fixes, so it would run before this gate re-scores; record the result, re-score per procedure step 5, and hand off through §Decision Bands if the dimension stays `\u003C 70`; invoke `ywc-debug-rootcause` only after the gate allows implementation |\n\nScope dimension `\u003C 50` does NOT have an advisor target — STOP on scope routes back to `ywc-plan` (Scale assessment) or `ywc-brainstorm` (intent surfacing) via §Decision Bands directly; an advisor cannot disambiguate scope without first knowing what the user actually wants.\n\n**Budget**: **1 advisor dispatch per gate run**. Even if multiple dimensions score `\u003C 50`, dispatch the one with the lowest absolute score (or the architecturally most foundational — architecture > root cause > evidence > reuse) and let its verdict propagate through re-scoring. Multiple dispatches in one gate run defeat the bounded-payload discipline by accumulating context across iterations.\n\n**When NOT to dispatch**:\n\n- `band == STOP` with no dimension `\u003C 50` (the STOP came purely from aggregate `\u003C 70`) — hand off to the upstream skill listed in §Decision Bands directly.\n- The framed gap has no decision-altering answer (Step 1 \"nothing would change with an answer\") — dispatch wastes a budgeted call.\n- The same dispatch already ran in the immediately preceding gate run on the same work item — accept the prior verdict as still valid and use §Decision Bands directly.\n\n## Output Format\n\n```text\nConfidence Gate Report\n──────────────────────\nAggregate: \u003CNN>\u002F100 — \u003CPROCEED | REVIEW | STOP>\n\n  Scope clarity:           \u003CNN>   \u003Cone-line evidence>\n  Architecture compliance: \u003CNN>   \u003Cone-line evidence>\n  Evidence quality:        \u003CNN>   \u003Cone-line evidence>\n  Reuse verified:          \u003CNN>   \u003Cone-line evidence>\n  Root cause identified:   \u003CNN>   \u003Cone-line evidence>\n\n\u003CIf REVIEW or STOP:>\nWeakest dimension: \u003Cname> (\u003CNN>)\nWhy: \u003Cone or two sentences explaining what is missing>\nWhat would raise it: \u003Cconcrete evidence or action — file to read, command to run, question to ask>\n\n\u003CIf REVIEW:>\nAlternatives presented for user decision:\n  A. \u003Coption> — trade-off\n  B. \u003Coption> — trade-off\n  (C. \u003Coption> — trade-off)\n\n\u003CIf STOP:>\nRouting: \u003Cywc-plan | ywc-spec-validate | ywc-tech-research | ywc-brainstorm> — \u003Cwhy>\n```\n\nThe \"Weakest dimension\" and \"What would raise it\" lines are **mandatory** whenever the band is REVIEW or STOP. They are the mechanism that turns the gate from a roadblock into a step-by-step path forward.\n\n## Integration\n\n- **Upstream callers**: user invocation; `ywc-plan` (after Scale assessment, before downstream handoff); `ywc-code-gen` (Step 0, before Reuse Gate); `ywc-sequential-executor` \u002F `ywc-parallel-executor` (before per-task implementation begins, especially for tasks with no upstream `ywc-plan` evidence); `ywc-agentic` (per-iteration entry).\n- **Downstream**: implementation skills proceed on PROCEED; user dialog or Advisor Pattern on REVIEW; `ywc-plan` \u002F `ywc-spec-validate` \u002F `ywc-tech-research` \u002F `ywc-brainstorm` on STOP.\n- **Pairs with**: `ywc-verify-done` (the symmetric **post**-implementation gate — that gates the claim, this gates the start); `ywc-impl-review` (uses the same rubric for post-review confidence — scores remain comparable across the two gates).\n\n## Validation Checklist\n\nBefore reporting a PROCEED band and beginning implementation, verify:\n\n- [ ] All five dimensions have explicit numeric scores (not \"high\", not \"OK\")\n- [ ] Each dimension has a one-line evidence statement\n- [ ] No dimension scored at or below 50\n- [ ] Aggregate was computed with the rubric weights (25\u002F25\u002F20\u002F15\u002F15)\n- [ ] The single-dim override was applied if any score ≤ 50\n- [ ] The score and band are surfaced in the response **before** any implementation tool is invoked\n- [ ] If REVIEW or STOP, no implementation skill was invoked in the same turn\n\n## Common Mistakes\n\n(Procedural failure modes specific to this skill. Behavioral rationalizations are in the table above — do not duplicate here.)\n\n- **Scoring after the implementation already started in the same turn.** The report must appear before the first implementation tool call. Scoring after invokes the gate retroactively — at which point its primary value (preventing the call) is gone.\n- **Reporting only the aggregate, not the per-dimension breakdown.** A single number hides the weakest dimension; that is exactly the information the user needs to act. Always print all five dimension scores.\n- **Carrying an upstream skill's confidence forward instead of re-scoring.** Each skill boundary re-narrows the context. A PROCEED at `ywc-plan` does not automatically transfer to `ywc-code-gen`, because the code-gen step has its own dimensions to score (especially Reuse verified and Architecture compliance, which `ywc-plan` does not score as deeply).\n- **Treating REVIEW as a soft STOP.** REVIEW is \"proceed with explicit alternatives presented and one of them chosen\". STOP is \"do not proceed\". Conflating them collapses three bands into two and defeats the rubric's resolution.\n- **Adding a sixth dimension because \"my work has a unique aspect\".** The five dimensions are fixed across skills so scores remain comparable. Per-skill adjustments belong in the \"required dimensions\" profile (see `references\u002Fconfidence-gate.md` §4), not in extra dimensions.\n\n## References\n\n| Reference | Use when |\n|---|---|\n| [..\u002Freferences\u002Fconfidence-gate.md](..\u002Freferences\u002Fconfidence-gate.md) | Authoritative rubric definition; per-skill required-dimension profiles; status mapping; anti-patterns |\n| [references\u002Fpre-implementation-checklist.md](references\u002Fpre-implementation-checklist.md) | Per-dimension probe questions specific to the pre-implementation moment (this skill's distinct usage from the post-review usage in `ywc-impl-review`) |\n| [..\u002Freferences\u002Fadvisor-pattern.md](..\u002Freferences\u002Fadvisor-pattern.md) | Escalating a weak dimension to a higher-capability advisor for a second opinion before changing the band |\n| `ywc-verify-done` | The symmetric post-implementation gate; both gates use the same rubric so the start-of-work and end-of-work scores are directly comparable |\n",{"name":5,"description":7},"main","7e8ac872e53df8c89d75663e031626281a2a2f5c","plugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate",1,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit","https:\u002F\u002Fgithub.com\u002Fyongwoon","https:\u002F\u002Fwww.webhani.com","2026-11-08 17:14:59",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add yongwoon\u002Fywc-agent-toolkit --skill ywc-confidence-gate",{"tool":37,"command":38},"bunx","bunx skills add yongwoon\u002Fywc-agent-toolkit --skill ywc-confidence-gate",{"tool":40,"command":41},"pnpm","pnpm dlx skills add yongwoon\u002Fywc-agent-toolkit --skill ywc-confidence-gate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002FSKILL.md",true,[45,51,55,59,63,67,71,75,79],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",454,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"evals\u002Fevals.json",4333,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002Fevals\u002Fevals.json",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"README.en.md",3302,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002FREADME.en.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"README.es.md",895,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002FREADME.es.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"README.ja.md",3466,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002FREADME.ja.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"README.ko.md",3463,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002FREADME.ko.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"README.md",3456,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002FREADME.md",{"path":76,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":77,"sourceHtmlUrl":78},"README.zh.md",806,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002FREADME.zh.md",{"path":80,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fpre-implementation-checklist.md",7386,"https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-confidence-gate\u002Freferences\u002Fpre-implementation-checklist.md",[84,90,96,103,110,117],{"skillNo":85,"name":86,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M72TQ84GTCPCV2VJ778V17TW","missing-frontmatter","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fcodex-description-limit\u002Fmissing-frontmatter\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M72TQ6M4BFWE7P9EPW0GZDCM","malformed-frontmatter","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fcodex-description-limit\u002Fmalformed-frontmatter\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M72TQ3ESGKXZ4QRWGTX92BKJ","fixture-501-fail","(ywc) Use when aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa Do not use for x.","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fcodex-description-limit\u002F501-fail\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M72TQ0HJ8H3R37J9WPWGKJZR","fixture-500-pass","(ywc) Use when aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa Do not use for x.","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fcodex-description-limit\u002F500-pass\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":18},"01M72TPWNCC7NEYD0D9N12KSQS","ywc-worktrees","(ywc) Use when creating, auditing, pruning, or resolving git worktrees for isolated task workspaces, whether delegated from an executor or used standalone. Triggers: \"worktree 생성\", \"worktree audit\", \"worktree 정리\", \"worktree prune\", \"ywc-worktrees\", \"create worktree\". Do not use for branch creation\u002Fdeletion alone, PR creation (use ywc-create-pr), CI or merge delivery (use ywc-finish-branch), task orchestration (use ywc-sequential-executor or ywc-parallel-executor), or non-git isolation.","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-worktrees\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":18},"01M72TPRNR3E6QWB91GM98ABBV","ywc-wayfinder","(ywc) Use when a large or uncertain change needs multi-session discovery with a deterministic local map and exactly one active ticket before planning or implementation. Triggers: \"wayfinder\", \"길찾기\", \"discovery map\", \"multi-session discovery\", \"탐색 ticket\", \"経路整理\", \"探索マップ\", \"ywc-wayfinder\". Do not use for ordinary planning (use ywc-plan), idea clarification (use ywc-brainstorm), direct implementation, or tracker\u002Fdatabase writes outside the local Markdown map.","https:\u002F\u002Fgithub.com\u002Fyongwoon\u002Fywc-agent-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Fywc-agent-toolkit\u002Fskills\u002Fywc-wayfinder\u002FSKILL.md",[],[]]