[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71REEZ4SDNYMJCSCY9PBZFX":3,"skill-same:01M71REEZ4SDNYMJCSCY9PBZFX":90},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M71REEZ4SDNYMJCSCY9PBZFX","autospec-explore-ledger",null,"Use when the user wants to inspect, rebuild, or act on the autospec-explore outcome ledger — the recursive-self-improvement memory that records which research sources actually ship clean PRs, derives dynamic source weights, and produces a learnings memo. Subcommands — show, stats, rebuild, weights, learnings.","berlinguyinca\u002Fautospec","berlinguyinca","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F16364?v=4","01M71R7C0SWBG05FNHQE4XQ7Y3","Gert Wohlgemuth","01M71R7C1VY5K3Q715RNDDBVGQ",3,"MIT","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-explore-ledger\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"autospec","autospec explore","ledger","autospec explore ledger","explore","rebuild","stats","learnings","when","use","self-improvement","prs","clean","records","inspect","memory","improvement","show","which","sources","2026-11-10 13:02:02",false,"---\nname: autospec-explore-ledger\ndescription: Use when the user wants to inspect, rebuild, or act on the autospec-explore outcome ledger — the recursive-self-improvement memory that records which research sources actually ship clean PRs, derives dynamic source weights, and produces a learnings memo. Subcommands — show, stats, rebuild, weights, learnings.\n---\n\n# autospec-explore-ledger workflow (harness-neutral)\n\nOperator-facing surface for the **autospec-explore** outcome ledger — the\nrecursive-self-improvement (RSI) memory that closes the explore loop. The\nexplore loop files feature proposals from research sources; this ledger records\neach proposal's eventual outcome, turns those outcomes into per-source stats,\nderives dynamic Bayesian source weights, and regenerates a learnings memo. This\nskill is a thin, deterministic wrapper over three shell scripts: it inspects,\nrebuilds, and acts on that memory — it never files issues or runs the loop.\n\nManage your own context — never exceed 60%. These subcommands are deterministic\nshell calls; run them inline and report their output. Delegate only if a\nharness supports it and the output is large.\n\n## Self-update mode\n\nIf the argument matches the regex `^\\s*update\\s*$` (case-insensitive,\nwhitespace-padded), this skill enters self-update mode and does not run any\nsubcommand. This section is pure prose: never interpolate or shell out the\noperator's argument text.\n\n1. **Detect harness** by checking which install path exists for this skill:\n   - Claude Code: `~\u002F.claude\u002Fskills\u002Fautospec-explore-ledger\u002FSKILL.md`\n   - OpenCode:    `~\u002F.config\u002Fopencode\u002Fagent\u002Fautospec-explore-ledger.md`\n   - Codex CLI:   `~\u002F.codex\u002Fprompts\u002Fautospec-explore-ledger.md`\n2. **Re-install the full autospec suite from `main`** by piping the canonical installer:\n   ```bash\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fberlinguyinca\u002Fautospec\u002Fmain\u002Fbootstrap.sh | bash -s -- --skill all --harness all --update\n   ```\n   Run this one-liner once; it refreshes all autospec skills across all harnesses.\n3. **Show the diff** between the prior installed file(s) and the freshly fetched copy.\n4. **Stop.** Do not run any subcommand. Print the upgrade summary and return to the user.\n\nIf no install path is detected, print `Self-update: no installed copy of autospec-explore-ledger found; run install.sh first.` and exit.\n\n## Model tier\n\nTier A\u002FB model resolution and the harness-detection protocol are inherited\nverbatim from `AGENTS.md` (`## Subagent model selection (two-tier, cost-aware)`\nand `## Subagent vs inline decision matrix`). This skill is deterministic-first:\nevery subcommand is a shell call with no LLM dispatch. Only a free-form summary\nof a large `show`\u002F`stats` dump (if the operator asks for narrative) escalates to\na single Tier B pass — never Tier A.\n\n> **Model tier:** subcommands run deterministically with no dispatch; an optional narrative summary of ledger output runs at TIER_B (implementation work), resolved at startup per the harness detection below.\n\n### Required capabilities & harness adapter\n\nThis workflow assumes the following capabilities. Map each to your harness's\nactual tool; if a capability is missing, use the listed fallback.\n\n| Capability                  | Claude Code                             | OpenCode                              | Codex CLI                                | Fallback if missing                              |\n|-----------------------------|-----------------------------------------|---------------------------------------|------------------------------------------|--------------------------------------------------|\n| Run a shell command         | `Bash`                                  | shell tool                            | shell                                    | none — this skill requires a shell               |\n| Optional narrative summary  | `Agent` (subagent_type=general-purpose) | `task` agent, await output            | summarize inline (no subagents)          | Summarize in-thread (more context cost)          |\n| Ask the user a question     | `AskUserQuestion`                       | inline prompt                         | inline prompt                            | Ask in the response and wait for the next turn   |\n| Subagent model tier         | Tier A: `opus` + `ultrathink`; Tier B: `sonnet` + medium thinking | Tier A: top `task` model + high reasoning; Tier B: smaller-tier `task` + medium reasoning | Tier A: top GPT + `reasoning_effort=high`; Tier B: current spark\u002Fcost-optimized Codex + `reasoning_effort=medium` | Honor the per-phase tier mapping in AGENTS.md; retry the same subagent UP on unavailability |\n| Subagent dispatch policy    | per AGENTS.md decision matrix           | per AGENTS.md decision matrix         | per AGENTS.md decision matrix            | inline with main-session token cost              |\n\n**Persistent project notes**: write durable preferences to **`AGENTS.md`** in\nthe repo root — recognized by Claude Code, OpenCode, and Codex.\n\n## Harness detection (run once at skill start, before any subcommand)\n\nDetect your harness by checking available tools before any dispatch:\n\n1. **Claude Code** — the `Agent` tool with a `subagent_type` parameter is available.\n   - `TIER_A` = `opus` + `ultrathink`  (the alias, which resolves to the current Claude Opus generation)\n   - `TIER_B` = `sonnet`               (the alias, which resolves to the current Claude Sonnet generation)\n2. **OpenCode** — a `task` tool with model\u002Ftier configuration is available (no `subagent_type`).\n   - `TIER_A` = top-tier task model + high reasoning\n   - `TIER_B` = smaller-tier task model + medium reasoning\n3. **Codex CLI** — neither `Agent` nor a configurable `task` tool is available; work runs inline.\n   - `TIER_A` = current top GPT model + `reasoning_effort=high`\n   - `TIER_B` = the spark \u002F cost-optimized variant of the configured model when one exists, else the configured model + `reasoning_effort=medium`\n\n**Fallback rule:** If `TIER_B` is not available in your harness, silently retry\nthe same subagent dispatch with `TIER_A`. Preserve parent context on retry.\nNever ask the user.\n\nHold `TIER_A` and `TIER_B` for the entire skill run.\n\n## What this is\n\nThe autospec-explore loop files feature proposals from 6 research sources\n(spec\u002Fcode gaps, prior reports, codebase signals, open issues, repo source\nanalysis, competitor research). This ledger records each filed proposal's\neventual outcome — `merged_clean`, `qa_failed`, `reverted`, `stalled`, or\n`abandoned` — turning explore from an open loop into a closed, self-improving\none. Sources whose proposals ship clean in THIS repo gain ranking weight;\nsources with repeat failures lose it. The ledger is append-only: outcomes are\nrecorded as new entries, and readers take the latest entry per proposal.\n\n## Subcommands\n\nResolve the scripts at `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002F\u003Cscript>`.\n\n| Subcommand | Runs | Purpose |\n|---|---|---|\n| `show [--source X]` | `explore-ledger.sh --show` | inspect recorded outcomes (optionally for one source) |\n| `stats` | `explore-ledger.sh --stats` | per-source filed\u002Fclean\u002Ffailed counts |\n| `rebuild [--repo R]` | `explore-ledger.sh --rebuild` | reconstruct the ledger from GitHub issue\u002FPR history (writes `\u003Cledger>.rebuilt` if a live ledger exists) |\n| `weights` | `explore-source-weights.sh --json --explain` | show current dynamic source weights (and the math) |\n| `learnings` | `explore-learnings.sh` | (re)generate `.autospec\u002Fexplore-learnings.md` and print it |\n\n- `show [--source X]` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-ledger.sh --show` (append `--source X` to filter to one source). Print the recorded outcomes.\n- `stats` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-ledger.sh --stats`. Print the per-source filed\u002Fclean\u002Ffailed table.\n- `rebuild [--repo R]` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-ledger.sh --rebuild` (append `--repo R` to target a specific repo). If a live ledger already exists, the script writes the reconstruction to `\u003Cledger>.rebuilt` rather than clobbering it; report that path so the operator can diff and promote it.\n- `weights` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-source-weights.sh --json --explain`. Print the JSON weight map and the per-source explanation lines.\n- `learnings` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-learnings.sh`. It (re)derives `.autospec\u002Fexplore-learnings.md`; print the resulting memo path and contents.\n\nIf the operator gives no subcommand, default to `stats` (the cheapest at-a-glance view) and list the other subcommands.\n\n## How the loop closes\n\n1. **File** — a researcher files a proposal issue carrying a `\u003C!-- explore-ledger ... -->` marker in its body; explore records a `pending` ledger entry keyed on the issue.\n2. **Drain** — `\u002Fautospec-run` implements the issue and opens a PR against the sandbox branch.\n3. **Resolve** — when the PR merges, reverts, fails QA, stalls, or is abandoned, the outcome is recorded as a new append-only entry (`--update-outcome`).\n4. **Stats** — `stats` aggregates filed\u002Fclean\u002Ffailed counts per source from the latest entry per proposal.\n5. **Weights** — `weights` turns those counts into a dynamic Bayesian per-source weight that biases the NEXT round's proposal ranking.\n6. **Learnings** — `learnings` distills the same history into `.autospec\u002Fexplore-learnings.md` for human review.\n\nThe ledger lives at `.autospec\u002Fexplore-ledger.jsonl` (gitignored runtime memory;\noverride with `AUTOSPEC_EXPLORE_LEDGER`). All ledger operations are best-effort:\na missing or empty ledger yields empty stats\u002Fweights, never a hard failure.\n\n## Finalization\n\nPrint which subcommand ran and the relevant path(s):\n\n- `show` \u002F `stats` \u002F `weights` — the ledger path read (`.autospec\u002Fexplore-ledger.jsonl`).\n- `rebuild` — the written path (the live ledger, or `\u003Cledger>.rebuilt` when a live ledger was preserved).\n- `learnings` — the memo path (`.autospec\u002Fexplore-learnings.md`).\n","# autospec-explore-ledger workflow (harness-neutral)\n\nOperator-facing surface for the **autospec-explore** outcome ledger — the\nrecursive-self-improvement (RSI) memory that closes the explore loop. The\nexplore loop files feature proposals from research sources; this ledger records\neach proposal's eventual outcome, turns those outcomes into per-source stats,\nderives dynamic Bayesian source weights, and regenerates a learnings memo. This\nskill is a thin, deterministic wrapper over three shell scripts: it inspects,\nrebuilds, and acts on that memory — it never files issues or runs the loop.\n\nManage your own context — never exceed 60%. These subcommands are deterministic\nshell calls; run them inline and report their output. Delegate only if a\nharness supports it and the output is large.\n\n## Self-update mode\n\nIf the argument matches the regex `^\\s*update\\s*$` (case-insensitive,\nwhitespace-padded), this skill enters self-update mode and does not run any\nsubcommand. This section is pure prose: never interpolate or shell out the\noperator's argument text.\n\n1. **Detect harness** by checking which install path exists for this skill:\n   - Claude Code: `~\u002F.claude\u002Fskills\u002Fautospec-explore-ledger\u002FSKILL.md`\n   - OpenCode:    `~\u002F.config\u002Fopencode\u002Fagent\u002Fautospec-explore-ledger.md`\n   - Codex CLI:   `~\u002F.codex\u002Fprompts\u002Fautospec-explore-ledger.md`\n2. **Re-install the full autospec suite from `main`** by piping the canonical installer:\n   ```bash\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fberlinguyinca\u002Fautospec\u002Fmain\u002Fbootstrap.sh | bash -s -- --skill all --harness all --update\n   ```\n   Run this one-liner once; it refreshes all autospec skills across all harnesses.\n3. **Show the diff** between the prior installed file(s) and the freshly fetched copy.\n4. **Stop.** Do not run any subcommand. Print the upgrade summary and return to the user.\n\nIf no install path is detected, print `Self-update: no installed copy of autospec-explore-ledger found; run install.sh first.` and exit.\n\n## Model tier\n\nTier A\u002FB model resolution and the harness-detection protocol are inherited\nverbatim from `AGENTS.md` (`## Subagent model selection (two-tier, cost-aware)`\nand `## Subagent vs inline decision matrix`). This skill is deterministic-first:\nevery subcommand is a shell call with no LLM dispatch. Only a free-form summary\nof a large `show`\u002F`stats` dump (if the operator asks for narrative) escalates to\na single Tier B pass — never Tier A.\n\n> **Model tier:** subcommands run deterministically with no dispatch; an optional narrative summary of ledger output runs at TIER_B (implementation work), resolved at startup per the harness detection below.\n\n### Required capabilities & harness adapter\n\nThis workflow assumes the following capabilities. Map each to your harness's\nactual tool; if a capability is missing, use the listed fallback.\n\n| Capability                  | Claude Code                             | OpenCode                              | Codex CLI                                | Fallback if missing                              |\n|-----------------------------|-----------------------------------------|---------------------------------------|------------------------------------------|--------------------------------------------------|\n| Run a shell command         | `Bash`                                  | shell tool                            | shell                                    | none — this skill requires a shell               |\n| Optional narrative summary  | `Agent` (subagent_type=general-purpose) | `task` agent, await output            | summarize inline (no subagents)          | Summarize in-thread (more context cost)          |\n| Ask the user a question     | `AskUserQuestion`                       | inline prompt                         | inline prompt                            | Ask in the response and wait for the next turn   |\n| Subagent model tier         | Tier A: `opus` + `ultrathink`; Tier B: `sonnet` + medium thinking | Tier A: top `task` model + high reasoning; Tier B: smaller-tier `task` + medium reasoning | Tier A: top GPT + `reasoning_effort=high`; Tier B: current spark\u002Fcost-optimized Codex + `reasoning_effort=medium` | Honor the per-phase tier mapping in AGENTS.md; retry the same subagent UP on unavailability |\n| Subagent dispatch policy    | per AGENTS.md decision matrix           | per AGENTS.md decision matrix         | per AGENTS.md decision matrix            | inline with main-session token cost              |\n\n**Persistent project notes**: write durable preferences to **`AGENTS.md`** in\nthe repo root — recognized by Claude Code, OpenCode, and Codex.\n\n## Harness detection (run once at skill start, before any subcommand)\n\nDetect your harness by checking available tools before any dispatch:\n\n1. **Claude Code** — the `Agent` tool with a `subagent_type` parameter is available.\n   - `TIER_A` = `opus` + `ultrathink`  (the alias, which resolves to the current Claude Opus generation)\n   - `TIER_B` = `sonnet`               (the alias, which resolves to the current Claude Sonnet generation)\n2. **OpenCode** — a `task` tool with model\u002Ftier configuration is available (no `subagent_type`).\n   - `TIER_A` = top-tier task model + high reasoning\n   - `TIER_B` = smaller-tier task model + medium reasoning\n3. **Codex CLI** — neither `Agent` nor a configurable `task` tool is available; work runs inline.\n   - `TIER_A` = current top GPT model + `reasoning_effort=high`\n   - `TIER_B` = the spark \u002F cost-optimized variant of the configured model when one exists, else the configured model + `reasoning_effort=medium`\n\n**Fallback rule:** If `TIER_B` is not available in your harness, silently retry\nthe same subagent dispatch with `TIER_A`. Preserve parent context on retry.\nNever ask the user.\n\nHold `TIER_A` and `TIER_B` for the entire skill run.\n\n## What this is\n\nThe autospec-explore loop files feature proposals from 6 research sources\n(spec\u002Fcode gaps, prior reports, codebase signals, open issues, repo source\nanalysis, competitor research). This ledger records each filed proposal's\neventual outcome — `merged_clean`, `qa_failed`, `reverted`, `stalled`, or\n`abandoned` — turning explore from an open loop into a closed, self-improving\none. Sources whose proposals ship clean in THIS repo gain ranking weight;\nsources with repeat failures lose it. The ledger is append-only: outcomes are\nrecorded as new entries, and readers take the latest entry per proposal.\n\n## Subcommands\n\nResolve the scripts at `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002F\u003Cscript>`.\n\n| Subcommand | Runs | Purpose |\n|---|---|---|\n| `show [--source X]` | `explore-ledger.sh --show` | inspect recorded outcomes (optionally for one source) |\n| `stats` | `explore-ledger.sh --stats` | per-source filed\u002Fclean\u002Ffailed counts |\n| `rebuild [--repo R]` | `explore-ledger.sh --rebuild` | reconstruct the ledger from GitHub issue\u002FPR history (writes `\u003Cledger>.rebuilt` if a live ledger exists) |\n| `weights` | `explore-source-weights.sh --json --explain` | show current dynamic source weights (and the math) |\n| `learnings` | `explore-learnings.sh` | (re)generate `.autospec\u002Fexplore-learnings.md` and print it |\n\n- `show [--source X]` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-ledger.sh --show` (append `--source X` to filter to one source). Print the recorded outcomes.\n- `stats` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-ledger.sh --stats`. Print the per-source filed\u002Fclean\u002Ffailed table.\n- `rebuild [--repo R]` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-ledger.sh --rebuild` (append `--repo R` to target a specific repo). If a live ledger already exists, the script writes the reconstruction to `\u003Cledger>.rebuilt` rather than clobbering it; report that path so the operator can diff and promote it.\n- `weights` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-source-weights.sh --json --explain`. Print the JSON weight map and the per-source explanation lines.\n- `learnings` — run `${AUTOSPEC_SCRIPTS_DIR:-$HOME\u002F.autospec\u002Fscripts}\u002Fexplore-learnings.sh`. It (re)derives `.autospec\u002Fexplore-learnings.md`; print the resulting memo path and contents.\n\nIf the operator gives no subcommand, default to `stats` (the cheapest at-a-glance view) and list the other subcommands.\n\n## How the loop closes\n\n1. **File** — a researcher files a proposal issue carrying a `\u003C!-- explore-ledger ... -->` marker in its body; explore records a `pending` ledger entry keyed on the issue.\n2. **Drain** — `\u002Fautospec-run` implements the issue and opens a PR against the sandbox branch.\n3. **Resolve** — when the PR merges, reverts, fails QA, stalls, or is abandoned, the outcome is recorded as a new append-only entry (`--update-outcome`).\n4. **Stats** — `stats` aggregates filed\u002Fclean\u002Ffailed counts per source from the latest entry per proposal.\n5. **Weights** — `weights` turns those counts into a dynamic Bayesian per-source weight that biases the NEXT round's proposal ranking.\n6. **Learnings** — `learnings` distills the same history into `.autospec\u002Fexplore-learnings.md` for human review.\n\nThe ledger lives at `.autospec\u002Fexplore-ledger.jsonl` (gitignored runtime memory;\noverride with `AUTOSPEC_EXPLORE_LEDGER`). All ledger operations are best-effort:\na missing or empty ledger yields empty stats\u002Fweights, never a hard failure.\n\n## Finalization\n\nPrint which subcommand ran and the relevant path(s):\n\n- `show` \u002F `stats` \u002F `weights` — the ledger path read (`.autospec\u002Fexplore-ledger.jsonl`).\n- `rebuild` — the written path (the live ledger, or `\u003Cledger>.rebuilt` when a live ledger was preserved).\n- `learnings` — the memo path (`.autospec\u002Fexplore-learnings.md`).\n",{"name":5,"description":7},"main","9e7f04357ff46ab731d4f56a4ac5ca5449c13bb0","skills\u002Fautospec-explore-ledger",1,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec","https:\u002F\u002Fgithub.com\u002Fberlinguyinca","Love to lead, code, cook and contribute to open source and believe that you can learn anything you set your mind too.\r\n","2026-11-11 07:09:35",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add berlinguyinca\u002Fautospec --skill autospec-explore-ledger",{"tool":58,"command":59},"bunx","bunx skills add berlinguyinca\u002Fautospec --skill autospec-explore-ledger",{"tool":61,"command":62},"pnpm","pnpm dlx skills add berlinguyinca\u002Fautospec --skill autospec-explore-ledger","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-explore-ledger\u002FSKILL.md",true,[66,72,78,82,86],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"codex\u002Fprompt.md","REFERENCE","参考文档",9714,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-explore-ledger\u002Fcodex\u002Fprompt.md",{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"install.sh","SCRIPT","脚本",10857,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-explore-ledger\u002Finstall.sh",{"path":79,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":80,"sourceHtmlUrl":81},"opencode\u002Fagent.md",9993,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-explore-ledger\u002Fopencode\u002Fagent.md",{"path":83,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":84,"sourceHtmlUrl":85},"README.md",4730,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-explore-ledger\u002FREADME.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"uninstall.sh",4041,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-explore-ledger\u002Funinstall.sh",[91,104,113,122,148,172],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":101,"publishedAt":39},"01M71RJHYMKPTC9AAPXWQ6F4RT","trio-pass-skill","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flockstep-trio-pass\u002FSKILL.md",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[102,103],"trio","trio pass skill",{"skillNo":105,"name":106,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":110,"publishedAt":39},"01M71RJFBQ1KAF9XM3T3Y4VMSK","duo-pass-skill","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flockstep-duo-pass\u002FSKILL.md",[109],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},[111,112],"duo pass skill","duo",{"skillNo":114,"name":115,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":119,"publishedAt":39},"01M71RJDT1TB3P9TRWR6A534FB","duo-divergence-skill","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flockstep-duo-divergence\u002FSKILL.md",[118],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},[120,112,121],"duo divergence skill","divergence",{"skillNo":123,"name":19,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":130,"publishedAt":39},"01M71RJAC4NNEQSYBDSY3NZS73","Use when the user wants to ship a feature end-to-end across multiple commits — bootstraps repo if missing, brainstorms a design spec, decomposes into linked GitHub issues, or splits an existing spec into issues, then runs an autonomous implementation loop with auto-merge.","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec\u002FSKILL.md",[127],{"categoryNo":128,"categoryName":129,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000015","视觉设计",[19,131,132,133,134,135,136,137,27,138,139,140,141,142,143,144,145,146,147,28],"ship a feature","end","issues","design","autonomous","auto","loop","across","design spec","merge","ship","implementation loop","github issues","feature","commits","repo","missing",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":39},"01M71RJ4F9HT8PT26CKNM9XE1M","autospec-upgrade","Use when the user wants to upgrade an Angular, Next.js, or React project to the latest official versions safely — by locking observable behavior before touching versions, upgrading one major at a time with official codemods, and gating completion on mutation score rather than coverage theater.","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-upgrade\u002FSKILL.md",[],[155,19,156,157,158,159,160,161,162,27,163,164,165,166,28,167,168,169,170,171],"autospec upgrade","upgrade","mutation","coverage","official","project","time","gating","angular","react","next","at","Next.js","one","with","behavior","latest",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":183,"publishedAt":39},"01M71RJ28FJ4PM6DXHB7T5CF8H","autospec-ui-audit","Use when a React Router application needs a deterministic whole-site route inventory before UI, UX, navigation, or evidence auditing begins.","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-ui-audit\u002FSKILL.md",[178],{"categoryNo":179,"categoryName":180,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[184,19,185,186,187,28,188,189,190,191,192,193,194,195,196,164,197,27,198],"ui audit","audit","autospec ui audit","ui","inventory","evidence","deterministic","route","ux","site","react router","navigation","application","needs","router"]