[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79PJZY5SE22RFNWMKAD683R":3,"skill-same:01M79PJZY5SE22RFNWMKAD683R":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M79PJZY5SE22RFNWMKAD683R","session-stats",null,"Shows token usage, model distribution, turn count, duration, tool usage, tool errors, and frustration signals (correction phrases, stuck tool-call loops) for a Claude Code session. Use when the user asks about token usage, session cost, model breakdown, what tool errors happened, or whether they got stuck in a loop -- \"session stats\", \"how much did this session use\", \"what tool errors happened\", \"was I stuck in a loop\". For the full session profile (tasks, messages, summary) rather than usage stats alone, use session-detail instead.","AndreHahm\u002Fandres-cc-marketplace","AndreHahm","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F80748019?v=4","01M79N2VZJT9MAJ7K695C9VXQ4","01M79N2W06PFX8BSCQ592M8K8K",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsession-stats\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: session-stats\ndescription: >-\n  Shows token usage, model distribution, turn count, duration, tool usage,\n  tool errors, and frustration signals (correction phrases, stuck tool-call\n  loops) for a Claude Code session. Use when the user asks about token usage,\n  session cost, model breakdown, what tool errors happened, or whether they\n  got stuck in a loop -- \"session stats\", \"how much did this session use\",\n  \"what tool errors happened\", \"was I stuck in a loop\". For the full session\n  profile (tasks, messages, summary) rather than usage stats alone, use\n  session-detail instead.\nallowed-tools: Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_store.py\":*) Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_transcript.py\":*)\n---\n\n# Session Stats\n\nShow detailed statistics for a single session.\n\n## When to Use\n\n- Wants a token-usage\u002Fcost\u002Fmodel breakdown for one session, and nothing more\n- \"session stats\", \"how much did this session use\", \"model breakdown\"\n- Wants to know what tool errors happened in a session, or whether they got stuck in a repeated\n  tool-call loop or pushed back with a correction — \"what tool errors happened\", \"was I stuck in a\n  loop\", \"did I get frustrated in that session\"\n\n## When NOT to Use\n\n- The full session profile (tasks, messages, summary), not just usage stats → use `session-detail` instead\n- Interruption recovery, not error listing (\"my session crashed, help me continue\") → use\n  `session-recover` instead\n\n## Step 1: Resolve the session\n\nIf the user provides a session ID or path, use it directly. Otherwise, find the current session:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_store.py\" current\n```\n\nUse the `path` field from the result. This resolves the live session directly (via its own session\nID), not by matching the current directory against a project name — safe even when the current\nworking directory doesn't match where the session actually started (e.g. a worktree created mid-session).\n\n## Step 2: Run the stats script\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_transcript.py\" stats \u003Csession-jsonl-path>\n```\n\nFor tool errors or frustration signals instead of (or alongside) usage stats, run the matching\nsubcommand on the same session path:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_transcript.py\" errors \u003Csession-jsonl-path>\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_transcript.py\" irritation \u003Csession-jsonl-path>\n```\n\n## Step 3: Present results\n\nEach subcommand outputs its own JSON object. Present as a visual summary:\n\n- **`stats`** — duration and turns as headline stats; token usage as a breakdown (input, output,\n  cache read, cache create) with totals; model distribution as a list showing which models were used\n  and how many turns each; tool usage as a ranked list (most used first)\n- **`errors`** — a list of tool errors (timestamp, tool name, truncated error content); report the\n  count first, then the list\n- **`irritation`** — correction phrases (timestamp, matched phrase, excerpt) and stuck tool-call\n  loops (tool name, consecutive-call count); report both counts, then the details\n\nNote: Cost estimation is not available. Report raw token counts and model names only.\n\n`irritation`'s correction-phrase matching is a simple substring heuristic (case-insensitive, phrases\nlike \"wrong\", \"stop\", \"undo\") — it can false-positive on unrelated uses of those words. Present matches\nas signals to review, not confirmed frustration.\n\n## Testing & Validation\n\nEval suite: `evals\u002Fsession-stats\u002F` — 3 scenarios (tool-error reporting, token\u002Fmodel breakdown reporting,\nloop\u002Ffrustration detection), `skill-tester` Quick Workflow blind comparison, all passed. Eval 3 verified\nthe error\u002Ffrustration-detection capability is used (not a generic token summary) and reports concrete\nevidence, not a bare yes\u002Fno. `get_stats`\u002F`get_errors`\u002F`get_irritation_signals`'s own branching logic is\nadditionally directly unit-tested via `tests\u002Ftest_session_transcript.py`.\n\n**Last dated run record:** `evals\u002Fsession-stats\u002Fworkspace\u002Fiteration-1\u002Feval-{1,2,3}\u002Fwith_skill\u002Fgrading.json`,\n2026-09-03. `scripts\u002Fsmoke_test.py` structural self-check also passing as of the same date.\n\n**Verify this skill activates on:**\n- \"session stats\"\n- \"how much did this session use\"\n- \"what models were used in this session\"\n- \"what tool errors happened in that session\"\n- \"was I stuck in a loop\"\n\n**Verify it does NOT activate on:**\n- \"show me everything about this session\" (full profile) → `session-detail`\n- \"my session crashed, help me continue\" (interruption recovery, not error listing) → `session-recover`\n\n**Quality gates:**\n- [ ] Step 1's `current` call needs no `--format` flag — the command always emits JSON\n- [ ] `irritation` results are presented as signals to review, never as confirmed frustration\n- [ ] `errors` entries attribute the correct `tool_name` via `tool_use_id` matching, not silently \"unknown\"\n","# Session Stats\n\nShow detailed statistics for a single session.\n\n## When to Use\n\n- Wants a token-usage\u002Fcost\u002Fmodel breakdown for one session, and nothing more\n- \"session stats\", \"how much did this session use\", \"model breakdown\"\n- Wants to know what tool errors happened in a session, or whether they got stuck in a repeated\n  tool-call loop or pushed back with a correction — \"what tool errors happened\", \"was I stuck in a\n  loop\", \"did I get frustrated in that session\"\n\n## When NOT to Use\n\n- The full session profile (tasks, messages, summary), not just usage stats → use `session-detail` instead\n- Interruption recovery, not error listing (\"my session crashed, help me continue\") → use\n  `session-recover` instead\n\n## Step 1: Resolve the session\n\nIf the user provides a session ID or path, use it directly. Otherwise, find the current session:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_store.py\" current\n```\n\nUse the `path` field from the result. This resolves the live session directly (via its own session\nID), not by matching the current directory against a project name — safe even when the current\nworking directory doesn't match where the session actually started (e.g. a worktree created mid-session).\n\n## Step 2: Run the stats script\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_transcript.py\" stats \u003Csession-jsonl-path>\n```\n\nFor tool errors or frustration signals instead of (or alongside) usage stats, run the matching\nsubcommand on the same session path:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_transcript.py\" errors \u003Csession-jsonl-path>\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_transcript.py\" irritation \u003Csession-jsonl-path>\n```\n\n## Step 3: Present results\n\nEach subcommand outputs its own JSON object. Present as a visual summary:\n\n- **`stats`** — duration and turns as headline stats; token usage as a breakdown (input, output,\n  cache read, cache create) with totals; model distribution as a list showing which models were used\n  and how many turns each; tool usage as a ranked list (most used first)\n- **`errors`** — a list of tool errors (timestamp, tool name, truncated error content); report the\n  count first, then the list\n- **`irritation`** — correction phrases (timestamp, matched phrase, excerpt) and stuck tool-call\n  loops (tool name, consecutive-call count); report both counts, then the details\n\nNote: Cost estimation is not available. Report raw token counts and model names only.\n\n`irritation`'s correction-phrase matching is a simple substring heuristic (case-insensitive, phrases\nlike \"wrong\", \"stop\", \"undo\") — it can false-positive on unrelated uses of those words. Present matches\nas signals to review, not confirmed frustration.\n\n## Testing & Validation\n\nEval suite: `evals\u002Fsession-stats\u002F` — 3 scenarios (tool-error reporting, token\u002Fmodel breakdown reporting,\nloop\u002Ffrustration detection), `skill-tester` Quick Workflow blind comparison, all passed. Eval 3 verified\nthe error\u002Ffrustration-detection capability is used (not a generic token summary) and reports concrete\nevidence, not a bare yes\u002Fno. `get_stats`\u002F`get_errors`\u002F`get_irritation_signals`'s own branching logic is\nadditionally directly unit-tested via `tests\u002Ftest_session_transcript.py`.\n\n**Last dated run record:** `evals\u002Fsession-stats\u002Fworkspace\u002Fiteration-1\u002Feval-{1,2,3}\u002Fwith_skill\u002Fgrading.json`,\n2026-09-03. `scripts\u002Fsmoke_test.py` structural self-check also passing as of the same date.\n\n**Verify this skill activates on:**\n- \"session stats\"\n- \"how much did this session use\"\n- \"what models were used in this session\"\n- \"what tool errors happened in that session\"\n- \"was I stuck in a loop\"\n\n**Verify it does NOT activate on:**\n- \"show me everything about this session\" (full profile) → `session-detail`\n- \"my session crashed, help me continue\" (interruption recovery, not error listing) → `session-recover`\n\n**Quality gates:**\n- [ ] Step 1's `current` call needs no `--format` flag — the command always emits JSON\n- [ ] `irritation` results are presented as signals to review, never as confirmed frustration\n- [ ] `errors` entries attribute the correct `tool_name` via `tool_use_id` matching, not silently \"unknown\"\n",{"name":5,"description":7,"allowed-tools":23},"Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_store.py\":*) Bash(python3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fsession_transcript.py\":*)","main","1bf12900cac6f28e346abd2912bdb78d306de723",".claude\u002Fskills\u002Fsession-stats","https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace","https:\u002F\u002Fgithub.com\u002FAndreHahm","2026-11-15 04:26:16",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add AndreHahm\u002Fandres-cc-marketplace --skill session-stats",{"tool":36,"command":37},"bunx","bunx skills add AndreHahm\u002Fandres-cc-marketplace --skill session-stats",{"tool":39,"command":40},"pnpm","pnpm dlx skills add AndreHahm\u002Fandres-cc-marketplace --skill session-stats","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsession-stats\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fsmoke_test.py","SCRIPT","脚本",7975,"https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsession-stats\u002Fscripts\u002Fsmoke_test.py",[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":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M79R0K918Z0XDM74R0EY5H3P","demo","Fixture skill used by scripts.marketplace_ci sync tests.","https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002Ftests\u002Fmarketplace_ci\u002Ffixtures\u002Fplugins\u002Fsample-kit\u002Fskills\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M79R08VMDJA2FPJKH3ZM309K","export-demo","Fixture skill used by scripts.marketplace_ci export tests.","https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002Ftests\u002Fmarketplace_ci\u002Ffixtures\u002Fclaude\u002Fskills\u002Fexport-demo\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M79R042FS581DS2JNW5AZ1MK","work-to-development","Validate an accepted Linear Issue's readiness for implementation (criteria, dependencies, duplicate\u002Fexisting artifacts) and request governed branch\u002Fworktree creation through git-kit:starting-work — recording work-started Git\u002FGitHub evidence and a deliberate Linear Started transition only after Git identity is read back and verified. Use when asked to start work on a Linear issue, begin development for an accepted issue, or prepare an accepted issue for implementation. Never creates a branch directly — always delegates to git-kit.","https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkmanagement-kit\u002Fskills\u002Fwork-to-development\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M79QZZD4EHB82P72P4N92BKT","work-linking","Create and maintain stable cross-system links and authority labels between Notion and Linear records, and detect\u002Frepair drift between them. Use when asked to link a Notion record to a Linear record, check for drift between Notion and Linear, or repair a broken\u002Fstale link. Repairs only the bounded non-authoritative copy or link — never chooses by newest timestamp, and never creates a reverse-write loop against either system's own authority.","https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkmanagement-kit\u002Fskills\u002Fwork-linking\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M79QZVFA3GTVNZMJ51NESVSP","status-and-learning","Produce a dated, explicitly non-live Linear-to-Notion progress summary, or capture an outcome\u002Flearning after work completes. Use when asked to summarize progress to Notion, report portfolio status, or capture what was learned from a completed piece of work — not to disposition open follow-up items (see open-item-management for that). Never runs automatically or continuously — every summary is a deliberate, approved snapshot, not a live sync.","https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkmanagement-kit\u002Fskills\u002Fstatus-and-learning\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M79QZNSKSABK7X2PT93X8QT5","repository-gates","Discover, delegate, record, and invalidate this repository's actual Git\u002FGitHub lifecycle gates (pre-commit, pre-push, PR required checks, Codex delta review, review requirements, merge rights) and the repository-policy provider profile that maps governed operations to git-kit. Use when asked what gates apply to this repository, to discover repository policy before starting Wave 2 work, or to check whether prior gate evidence is still valid after new commits. Discovery and delegation only — never executes a gate's own internal logic, and never invents a gate the repository doesn't actually define (in particular, never assumes a \"Review Changes\" gate exists).","https:\u002F\u002Fgithub.com\u002FAndreHahm\u002Fandres-cc-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fworkmanagement-kit\u002Fskills\u002Frepository-gates\u002FSKILL.md",[],[]]