[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7APW7M76ZFSFRB4NA5MAT76":3,"skill-same:01M7APW7M76ZFSFRB4NA5MAT76":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7APW7M76ZFSFRB4NA5MAT76","forge-framing",null,"Governs problem decomposition and constraint extraction during the FORGE Frame phase. Use when the Reasoner enters Phase F to extract the core decision, classify its type, map hard\u002Fsoft constraints, set deliberation depth, and declare success criteria before any hypothesis work begins.","Rynaro\u002Fmagicite","Rynaro","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5271543?v=4","01M70CFYFMB316W23THVQAQ42M","Henrique A. Lavezzo","01M7APN2KCVWBNY727T57KR2ZJ",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fforge\u002Fskills\u002Fframing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: forge-framing\ndescription: Governs problem decomposition and constraint extraction during the FORGE Frame phase. Use when the Reasoner enters Phase F to extract the core decision, classify its type, map hard\u002Fsoft constraints, set deliberation depth, and declare success criteria before any hypothesis work begins.\nmetadata:\n  methodology: FORGE\n  phase: F\n---\n\n# Framing Methodology\n\nLoaded during the Frame phase. Governs how the Reasoner decomposes problems into tractable decision structures.\n\n## When to use\n\nLoad this skill at the start of Phase F (Frame). Use it to extract the core decision question, classify the decision type (`TRADE-OFF`, `FEASIBILITY`, `ROOT-CAUSE`, `CONFLICT-RESOLUTION`, `CONSTRAINT-SATISFACTION`, `RISK-ASSESSMENT`), map all hard and soft constraints, set the deliberation depth score (1–9), and write the success criteria checklist. Do not proceed to Phase O (Observe) until all five steps are complete. Do not use for the Reason, Gate, or Emit phases.\n\n---\n\n## Memory pre-flight (Frame — mission intake)\n\nBefore any decomposition work begins, call CRYSTALIUM recall to surface prior\nverdicts, known constraints, and recurring deliberation patterns for this project:\n\n```\nmcp__crystalium__recall(\n  scope    = { project: \u003Ccwd-project>, agent_class_visibility: \"forge\" },\n  query    = \u003Cthe decision question being framed>,\n  k        = 5,\n  layers   = [\"semantic\", \"episodic\", \"procedural\"]\n)\n```\n\nFold relevant hits (prior verdicts on related decisions, reversal conditions that\nhave already fired, recurring constraint patterns) into the evidence inventory\nbefore Step 1 below. Prior deliberation outputs surface at T1 episodic, making\nprior FORGE verdicts directly reusable.\n\n**Graceful skip:** if `mcp__crystalium__*` tools are unavailable (CRYSTALIUM not\ninstalled), proceed without memory — never hard-fail. FORGE is EIIS-standalone-\nconformant and works without CRYSTALIUM.\n\nSee `PERSONA.md` §\"Memory pre-flight\" for the always-loaded note. See `SPEC.md §9`\nfor the full memory protocol summary.\n\n---\n\n## Problem Decomposition Protocol\n\n### Step 1: Extract the Core Decision\n\nStrip away narrative to find the atomic question. Apply the **Specificity Test**:\n\n> If two competent engineers could interpret this question differently and produce contradictory verdicts, the framing is insufficiently specific.\n\nTransform vague questions into precise ones:\n\n| Vague | Specific |\n|-------|----------|\n| \"Should we use microservices?\" | \"Given our team of 4, a monolith at 50K LOC, and 3 independent deployment cadences, does decomposing services X, Y, Z reduce deployment risk enough to justify the operational overhead?\" |\n| \"Is this architecture scalable?\" | \"Can this architecture handle 10x current load (defined as N req\u002Fs) within the existing infrastructure budget of $M\u002Fmonth, without exceeding p99 latency of Xms?\" |\n| \"What caused this outage?\" | \"Which component in the request path between ingress and database was the first to degrade, and what trigger pushed it past its failure threshold?\" |\n\n### Step 2: Classify the Decision Type\n\nEach type activates different reasoning patterns in the Deliberation phase:\n\n| Type | Core Question Shape | Reasoning Pattern |\n|------|-------------------|-------------------|\n| `TRADE-OFF` | \"X vs Y given constraints C\" | Multi-criteria scoring with explicit weights |\n| `FEASIBILITY` | \"Can X be achieved under constraints C?\" | Constraint enumeration → bottleneck identification → existence proof or counterexample |\n| `ROOT-CAUSE` | \"Why did X happen?\" | Causal chain reconstruction → elimination of confounders |\n| `CONFLICT-RESOLUTION` | \"Agents\u002Fstakeholders disagree on X\" | Position extraction → shared-ground identification → arbitration |\n| `CONSTRAINT-SATISFACTION` | \"Find solution satisfying C1, C2, ... Cn\" | Constraint graph → feasibility region → optimization within region |\n| `RISK-ASSESSMENT` | \"What can go wrong with X?\" | Failure mode enumeration → likelihood × impact scoring → mitigation mapping |\n\n### Step 3: Map Constraints\n\nBuild the constraint table. Every constraint has a source and a hardness level:\n\n```markdown\n| ID | Constraint | Hard\u002FSoft | Source | Risk if Violated |\n|----|-----------|-----------|--------|-----------------|\n| C1 | p99 latency \u003C 200ms | Hard | SLA contract | Service credit penalties |\n| C2 | No new infrastructure spend | Soft | Q3 budget guidance | Deferral to Q4 |\n| C3 | Must work with PostgreSQL 14 | Hard | Ops team mandate | Migration blocked |\n```\n\n**Hard constraints** eliminate options. **Soft constraints** influence scoring but don't eliminate.\n\n### Step 4: Set Deliberation Depth\n\nScore the problem on three dimensions (1–3 each):\n\n| Dimension | 1 (Simple) | 2 (Standard) | 3 (Deep) |\n|-----------|-----------|--------------|----------|\n| **Ambiguity** | Clear right answer exists | 2–3 viable paths | Many viable paths, unclear winner |\n| **Reversibility** | Easy to undo | Moderate cost to reverse | Irreversible or very costly |\n| **Blast radius** | Single component | Multiple components | System-wide or organizational |\n\nTotal 3–4 → Simple (1 reasoning pass). Total 5–7 → Standard (2 passes). Total 8–9 → Deep (3 passes, extended token budget).\n\n### Step 5: Declare Success Criteria\n\nBefore reasoning begins, write down what \"done\" looks like:\n\n```markdown\n## Success Criteria\n- [ ] The verdict answers: [restate the specific question]\n- [ ] All hard constraints addressed with pass\u002Ffail\n- [ ] At least 3 alternatives evaluated with rejection reasons\n- [ ] Reversal conditions stated\n- [ ] Confidence score defensible\n- [ ] Requester can act without further clarification\n```\n\n---\n\n## Evidence Inventory Protocol\n\nCatalog every piece of provided context before reasoning:\n\n```markdown\n## Evidence Inventory\n\n| ID | Source | Type | Relevance | Reliability |\n|----|--------|------|-----------|-------------|\n| E1 | ATLAS scout-report.md | Scout report | Direct | H — evidence-anchored |\n| E2 | User-provided benchmark data | Performance data | Direct | M — methodology unstated |\n| E3 | Team Slack discussion | Stakeholder position | Contextual | L — informal, may be outdated |\n| E4 | SPECTRA spec v2 | Planning artifact | Direct | H — verified through SPECTRA gates |\n```\n\n**Reliability tiers:**\n- **H (High)** — Evidence-anchored artifacts, verified test results, official documentation\n- **M (Medium)** — Reasonable but unverified: benchmarks without methodology, expert opinions, dated documentation\n- **L (Low)** — Informal, secondhand, or potentially outdated sources\n\nClaims built on L-reliability evidence must carry `[ASSUMPTION]` markers.\n\n---\n\n## Anti-Patterns in Framing\n\n| Anti-Pattern | Signal | Remedy |\n|-------------|--------|--------|\n| **Binary framing** | \"Should we do X or not?\" | Expand to ≥3 options: do X, do Y, do nothing, do X-lite |\n| **Solution-first framing** | Question presupposes the answer | Re-frame around the problem, not the solution |\n| **Scope creep during framing** | Sub-questions multiply beyond the original ask | Constrain to the declared question; log expansions as follow-up verdicts |\n| **Missing stakeholders** | Constraints exist that nobody stated | Ask: \"Who else is affected? What would they say?\" |\n| **Phantom constraints** | Assumed constraints that nobody actually mandated | Verify every constraint has a named source |\n\n---\n\n*Reasoner — Framing Skill*\n","# Framing Methodology\n\nLoaded during the Frame phase. Governs how the Reasoner decomposes problems into tractable decision structures.\n\n## When to use\n\nLoad this skill at the start of Phase F (Frame). Use it to extract the core decision question, classify the decision type (`TRADE-OFF`, `FEASIBILITY`, `ROOT-CAUSE`, `CONFLICT-RESOLUTION`, `CONSTRAINT-SATISFACTION`, `RISK-ASSESSMENT`), map all hard and soft constraints, set the deliberation depth score (1–9), and write the success criteria checklist. Do not proceed to Phase O (Observe) until all five steps are complete. Do not use for the Reason, Gate, or Emit phases.\n\n---\n\n## Memory pre-flight (Frame — mission intake)\n\nBefore any decomposition work begins, call CRYSTALIUM recall to surface prior\nverdicts, known constraints, and recurring deliberation patterns for this project:\n\n```\nmcp__crystalium__recall(\n  scope    = { project: \u003Ccwd-project>, agent_class_visibility: \"forge\" },\n  query    = \u003Cthe decision question being framed>,\n  k        = 5,\n  layers   = [\"semantic\", \"episodic\", \"procedural\"]\n)\n```\n\nFold relevant hits (prior verdicts on related decisions, reversal conditions that\nhave already fired, recurring constraint patterns) into the evidence inventory\nbefore Step 1 below. Prior deliberation outputs surface at T1 episodic, making\nprior FORGE verdicts directly reusable.\n\n**Graceful skip:** if `mcp__crystalium__*` tools are unavailable (CRYSTALIUM not\ninstalled), proceed without memory — never hard-fail. FORGE is EIIS-standalone-\nconformant and works without CRYSTALIUM.\n\nSee `PERSONA.md` §\"Memory pre-flight\" for the always-loaded note. See `SPEC.md §9`\nfor the full memory protocol summary.\n\n---\n\n## Problem Decomposition Protocol\n\n### Step 1: Extract the Core Decision\n\nStrip away narrative to find the atomic question. Apply the **Specificity Test**:\n\n> If two competent engineers could interpret this question differently and produce contradictory verdicts, the framing is insufficiently specific.\n\nTransform vague questions into precise ones:\n\n| Vague | Specific |\n|-------|----------|\n| \"Should we use microservices?\" | \"Given our team of 4, a monolith at 50K LOC, and 3 independent deployment cadences, does decomposing services X, Y, Z reduce deployment risk enough to justify the operational overhead?\" |\n| \"Is this architecture scalable?\" | \"Can this architecture handle 10x current load (defined as N req\u002Fs) within the existing infrastructure budget of $M\u002Fmonth, without exceeding p99 latency of Xms?\" |\n| \"What caused this outage?\" | \"Which component in the request path between ingress and database was the first to degrade, and what trigger pushed it past its failure threshold?\" |\n\n### Step 2: Classify the Decision Type\n\nEach type activates different reasoning patterns in the Deliberation phase:\n\n| Type | Core Question Shape | Reasoning Pattern |\n|------|-------------------|-------------------|\n| `TRADE-OFF` | \"X vs Y given constraints C\" | Multi-criteria scoring with explicit weights |\n| `FEASIBILITY` | \"Can X be achieved under constraints C?\" | Constraint enumeration → bottleneck identification → existence proof or counterexample |\n| `ROOT-CAUSE` | \"Why did X happen?\" | Causal chain reconstruction → elimination of confounders |\n| `CONFLICT-RESOLUTION` | \"Agents\u002Fstakeholders disagree on X\" | Position extraction → shared-ground identification → arbitration |\n| `CONSTRAINT-SATISFACTION` | \"Find solution satisfying C1, C2, ... Cn\" | Constraint graph → feasibility region → optimization within region |\n| `RISK-ASSESSMENT` | \"What can go wrong with X?\" | Failure mode enumeration → likelihood × impact scoring → mitigation mapping |\n\n### Step 3: Map Constraints\n\nBuild the constraint table. Every constraint has a source and a hardness level:\n\n```markdown\n| ID | Constraint | Hard\u002FSoft | Source | Risk if Violated |\n|----|-----------|-----------|--------|-----------------|\n| C1 | p99 latency \u003C 200ms | Hard | SLA contract | Service credit penalties |\n| C2 | No new infrastructure spend | Soft | Q3 budget guidance | Deferral to Q4 |\n| C3 | Must work with PostgreSQL 14 | Hard | Ops team mandate | Migration blocked |\n```\n\n**Hard constraints** eliminate options. **Soft constraints** influence scoring but don't eliminate.\n\n### Step 4: Set Deliberation Depth\n\nScore the problem on three dimensions (1–3 each):\n\n| Dimension | 1 (Simple) | 2 (Standard) | 3 (Deep) |\n|-----------|-----------|--------------|----------|\n| **Ambiguity** | Clear right answer exists | 2–3 viable paths | Many viable paths, unclear winner |\n| **Reversibility** | Easy to undo | Moderate cost to reverse | Irreversible or very costly |\n| **Blast radius** | Single component | Multiple components | System-wide or organizational |\n\nTotal 3–4 → Simple (1 reasoning pass). Total 5–7 → Standard (2 passes). Total 8–9 → Deep (3 passes, extended token budget).\n\n### Step 5: Declare Success Criteria\n\nBefore reasoning begins, write down what \"done\" looks like:\n\n```markdown\n## Success Criteria\n- [ ] The verdict answers: [restate the specific question]\n- [ ] All hard constraints addressed with pass\u002Ffail\n- [ ] At least 3 alternatives evaluated with rejection reasons\n- [ ] Reversal conditions stated\n- [ ] Confidence score defensible\n- [ ] Requester can act without further clarification\n```\n\n---\n\n## Evidence Inventory Protocol\n\nCatalog every piece of provided context before reasoning:\n\n```markdown\n## Evidence Inventory\n\n| ID | Source | Type | Relevance | Reliability |\n|----|--------|------|-----------|-------------|\n| E1 | ATLAS scout-report.md | Scout report | Direct | H — evidence-anchored |\n| E2 | User-provided benchmark data | Performance data | Direct | M — methodology unstated |\n| E3 | Team Slack discussion | Stakeholder position | Contextual | L — informal, may be outdated |\n| E4 | SPECTRA spec v2 | Planning artifact | Direct | H — verified through SPECTRA gates |\n```\n\n**Reliability tiers:**\n- **H (High)** — Evidence-anchored artifacts, verified test results, official documentation\n- **M (Medium)** — Reasonable but unverified: benchmarks without methodology, expert opinions, dated documentation\n- **L (Low)** — Informal, secondhand, or potentially outdated sources\n\nClaims built on L-reliability evidence must carry `[ASSUMPTION]` markers.\n\n---\n\n## Anti-Patterns in Framing\n\n| Anti-Pattern | Signal | Remedy |\n|-------------|--------|--------|\n| **Binary framing** | \"Should we do X or not?\" | Expand to ≥3 options: do X, do Y, do nothing, do X-lite |\n| **Solution-first framing** | Question presupposes the answer | Re-frame around the problem, not the solution |\n| **Scope creep during framing** | Sub-questions multiply beyond the original ask | Constrain to the declared question; log expansions as follow-up verdicts |\n| **Missing stakeholders** | Constraints exist that nobody stated | Ask: \"Who else is affected? What would they say?\" |\n| **Phantom constraints** | Assumed constraints that nobody actually mandated | Verify every constraint has a named source |\n\n---\n\n*Reasoner — Framing Skill*\n",{"name":5,"metadata":24,"description":7},{"phase":25,"methodology":26},"F","FORGE","main","38c3a82583abf9806de764f89ac0099ad690933a",".eidolons\u002Fforge\u002Fskills\u002Fframing",0,"https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite","https:\u002F\u002Fgithub.com\u002FRynaro","https:\u002F\u002Fhlavezzo.me","A Code Alchemist with a passion for weaving tales and inscribing transmutation circles in pure code.","2026-10-14 02:35:37",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Rynaro\u002Fmagicite --skill forge-framing",{"tool":42,"command":43},"bunx","bunx skills add Rynaro\u002Fmagicite --skill forge-framing",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Rynaro\u002Fmagicite --skill forge-framing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fforge\u002Fskills\u002Fframing\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7AQ4GHJQVV8TJBJ8T1V7ZQ9","wine-dxvk-cache-clear","Clear a stale DXVK shader cache that is causing graphical corruption in a\nWine or Proton game. Use when: a game shows corrupted textures or shader\nflicker that started after a driver or DXVK version change.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Ftoy-registry\u002Fskills\u002Fwine-dxvk-cache-clear\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7AQ4CY1NHSMY1HCZ91387YY","steam-download-region-fix","Fix a Steam client stuck at very low download speed by changing its\ndownload region. Use when: Steam downloads are far below the local\ninternet speed for every game, not just one.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Ftoy-registry\u002Fskills\u002Fsteam-download-region-fix\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7AQ49P7Y0CDRSYMPVABX80K","proton-battleye-eac-toggle","Toggle BattlEye or Easy Anti-Cheat runtime support for a Steam Proton game.\nUse when: a multiplayer game refuses to launch with an anti-cheat error under Proton.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Ftoy-registry\u002Fskills\u002Fproton-battleye-eac-toggle\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7AQ45326FAP3X4Q86FK1X4N","vivi-verify-incoming","Load when reading any upstream artefact handed off to Vivi that carries a sibling .envelope.json. BLOCKING per ECL §6.2.2: the orchestrator MUST have verified the envelope's SHA-256 (eidolons verify-envelope --block \u002F eidolons run --verify) and recorded a verify_pass before dispatch. If no verify_pass exists for the message_id, or a verify_fail is present, REFUSE to process the payload and hand back to the orchestrator. Symmetric receiver gate — every Eidolon enforces it identically.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fvivi\u002Fskills\u002Fverify-incoming\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7AQ402861P0P3C2TEGFGMA1","vivi-parallel-tracks","Load ONLY under TRANCE authorization when the Plan phase yields N independent, non-overlapping implementation tracks (disjoint file sets). Operationalizes the TRANCE G4 form — parallel multi-track implementation in mandatory git-worktree isolation, max 5 clean-context tracks, a per-track verifier cascade, a non-fungible per-track ≤3 reflection budget, explicit stop conditions, and a single-threaded merge\u002Faggregation step. Absent TRANCE gating, Vivi runs exactly as today: single-track A→P→I→V→Δ\u002FR.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fvivi\u002Fskills\u002Fparallel-tracks\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7AQ3RH9BZF9ZMTC7VG5P7PB","vivi-methodology","Full Vivi cycle reference — A(nalyze) → P(lan) → I(mplement) → V(erify) → Δ(Delta)\u002FR(eflect). Use when the task is a non-trivial feature implementation in a brownfield codebase and you need the complete methodology reference: complexity routing, evidence-grounded planning rules, test-anchoring requirements, and failure-escalation thresholds.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fvivi\u002Fskills\u002Fmethodology\u002FSKILL.md",[],[]]