[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7540E0PVBAP37EBGGF9T1AC":3,"skill-same:01M7540E0PVBAP37EBGGF9T1AC":282},{"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":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":51,"updatedAt":52,"install":53,"resources":65},"01M7540E0PVBAP37EBGGF9T1AC","cleanmatic:telemetry",null,"Plain-Vietnamese read on how the PO's skills are actually used + whether their scripts\u002Fsubagents are healthy + a thin internal-quality proxy (did validate pass). Runs read-only lenses over local telemetry (invocations, sessions, script runs, subagent outcomes, memory) and narrates them honestly — usage & health, NOT market effectiveness. Outputs ascii\u002Fmarkdown\u002Fmermaid\u002Fjson.","hieubui2409\u002Fproduct-spec","hieubui2409","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F95897872?v=4","01M753ZEGHX9Y8QZZ0CR5GJG3E","Lucas Bui","01M753ZEHJ6Z55P0WSKRDAG3Y3",17,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: cleanmatic:telemetry\ndescription: \"Plain-Vietnamese read on how the PO's skills are actually used + whether their scripts\u002Fsubagents are healthy + a thin internal-quality proxy (did validate pass). Runs read-only lenses over local telemetry (invocations, sessions, script runs, subagent outcomes, memory) and narrates them honestly — usage & health, NOT market effectiveness. Outputs ascii\u002Fmarkdown\u002Fmermaid\u002Fjson.\"\nuser-invocable: true\nwhen_to_use: \"When the (non-technical) product owner asks how their skills are being used, which scripts error or run slow, whether subagents succeed, whether memory is tidy, or whether the last spec validate passed — and wants it explained in plain Vietnamese, not raw logs.\"\ncategory: observability\nkeywords: [telemetry, usage, health, skills, tokens, sessions, reliability, subagents, memory, validate, vietnamese, dashboard, analytics]\nargument-hint: \"[--lens usage|session|health|reliability|workflow|validate|memory|product_memory|artifact_heat|forensics|all] [--format ascii|md|mermaid|json] [--days N] [--top N] [--lang vi|en]\"\nmetadata:\n  author: cleanmatic\n  version: \"1.1.1\"\n---\n\n# cleanmatic:telemetry — Usage & Health (Mức dùng & Sức khỏe)\n\nA **read-only** skill that tells the product owner, **in plain Vietnamese**, three things about their own tooling:\n\n1. **Mức dùng (Usage)** — which skills get used (and how often), token weight per skill, and which skills are never touched.\n2. **Sức khỏe (Health)** — which scripts error or run slow (approx), whether subagents succeed\u002Ffail, whether memory is tidy.\n3. **Một tín hiệu chất lượng nội bộ (a thin internal-quality proxy)** — after a `product-spec` run, did `validate` pass.\n\n**Honest framing — this is \"mức dùng & sức khỏe\", NOT \"hiệu quả\".** It measures *whether the machinery runs*, never *whether the product wins in the market*. (Product-outcome tracking shipped separately as `product-spec --learn`, but even that records PO-declared outcomes vs goals offline — still NOT a market-effectiveness metric.) The narration MUST keep that line bright (see the honesty gate below).\n\n## What this is NOT\n\n- **Not** a market\u002Fuser-outcome metric. The validate proxy = \"spec is well-formed\", not \"users adopted it\". (PO-declared outcome tracking lives in `product-spec --learn`; this skill does not read it.)\n- **Not** a writer — it never edits specs, code, the catalog, or memory. No `--apply`, no fixes.\n- **Not** billing-exact — token attribution and `ms` durations are **directional\u002Fapprox**.\n- **Not** a CI gate — opinion-free numbers for the PO to read, nothing blocks on it.\n\n## How it runs (deterministic gather → LLM narrates)\n\nThe split both repos follow: a **script gathers** (deterministic, never judges), the **skill narrates** (judges, in VI). The skill NEVER recomputes a number — it narrates the script's dict.\n\n```bash\n# Recipient bundle: system python3 with PyYAML (the bundle's single runtime dep, shipped via product-spec).\npython3 .\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Fanalyze_telemetry.py \\\n  --lens all --format ascii [--days 30] [--top 10]\n# In the cleanmatic dev repo, use the shared venv: .\u002F.claude\u002Fskills\u002F.venv\u002Fbin\u002Fpython3 …\n```\n\nDefault behaviour when the PO invokes `\u002Fcleanmatic:telemetry`:\n1. Run `analyze_telemetry.py --lens all --format ascii`.\n2. Read the aggregates; **narrate in Vietnamese** (default). Switch to English with `--lang en` (the script also localizes its fixed labels) or just \"in English\".\n3. Lead with the honesty gate; recommendations are **gợi ý (suggestions)** only.\n\nPass-through flags: `--lens \u003Cname>`, `--format md|mermaid|json`, `--days N`, `--top N`, `--lang vi|en` (fixed-label language, vi default), `--session \u003Cid>` \u002F `--all-sessions` (forensics). Runs under system `python3`; needs PyYAML (the bundle's single runtime dependency, shipped with product-spec).\n\n## Lenses\n\n| `--lens`     | Reads (sink)                          | Surfaces |\n|--------------|---------------------------------------|----------|\n| `usage`      | `invocations.jsonl` + transcripts     | invocation counts, per-skill tokens (approx), never-used catalog |\n| `session`    | `sessions.jsonl`                      | session count, avg\u002Fmedian duration, files, subagents, skill co-occurrence |\n| `health`     | `hook-telemetry.jsonl`                | per-script runs\u002Ferrors\u002Ferror-rate + avg `ms` (approx) |\n| `reliability`| `subagent-outcomes.jsonl`             | subagent success \u002F api_error \u002F timeout \u002F blocked \u002F unknown per type |\n| `workflow`   | `invocations.jsonl` + `data\u002Fskill-chains.yaml` | actual skill chains vs declared chains; deviations |\n| `validate`   | `last_validated.json` + `hook-telemetry` | validate-pass proxy (internal quality, NOT market outcome) |\n| `memory`     | `~\u002F.claude\u002Fprojects\u002F\u003Croot>\u002Fmemory\u002F`   | orphans, dead index entries, broken `[[links]]`, staleness (read-only) |\n| `product_memory` | `docs\u002Fproduct\u002F.memory\u002F`           | spec-store health: last-validated age, missing state files, critique-cache size (read-only) |\n| `artifact_heat` | `artifact-events.jsonl`            | artifact-edit frequency: most-edited spec artifacts (heat ranking), within `--days` window |\n| `forensics`  | session transcript JSONL              | one session reconstructed (skills\u002Ftools\u002Ftokens\u002Ffiles\u002Fduration) |\n| `all`        | the above (minus forensics)           | the dashboard-lite the PO reads first |\n\n## Low-volume gate (chưa đủ dữ liệu)\n\nBelow ~5 data points a lens shows raw counts + **\"chưa đủ dữ liệu\"** and **suppresses recommendations**. On a thin\u002Fnew repo most lenses WILL be gated — say so plainly; do not invent trends.\n\n## Narration & honesty gate (mandatory)\n\nDetailed rubric: `references\u002Fnarration-contract.md`. The non-negotiable parts:\n\n- **Separate MEASURED from NOT-MEASURED.** Every report MUST end with a section **\"Cái này KHÔNG đo được\"** naming at minimum: market\u002Fuser outcome (this skill measures usage\u002Fhealth, not market effectiveness); plus any lens that is empty\u002Fgated on current data → call it \"chưa đủ dữ liệu\", never spin it.\n- **Approx is approx.** Token weight, `ms`, and `exit` are inferred\u002Fdirectional — say \"ước lượng\", never present them as exact.\n- **Suggestions, not verdicts.** Phrase any action as a gợi ý the PO may ignore; the skill has no authority to prune skills, edit memory, or change scope.\n- **VI is native-quality** — correct diacritics, natural register for a non-technical owner; numbers stay numbers, skill ids stay ascii.\n\n## Hook config & crash log\n\nThe 7 project Python hooks (5 telemetry + 2 enforcement) share one runtime,\n`.claude\u002Fhooks\u002Fhook_runtime.py`, and one per-hook on\u002Foff file,\n`.claude\u002Fhooks\u002Fproduct-spec-hooks.json` (key = the hook's filename stem):\n\n| Hook stem (key)                | Kind        | Default when key missing |\n|--------------------------------|-------------|--------------------------|\n| `mark_bash_start`              | telemetry   | **enabled**              |\n| `track_skill_invocation`       | telemetry   | **enabled** (one key gates BOTH its registrations: PreToolUse:Skill + UserPromptExpansion) |\n| `track_script_execution`       | telemetry   | **enabled**              |\n| `track_subagent_outcome`       | telemetry   | **enabled**              |\n| `emit_session_summary`         | telemetry   | **enabled**              |\n| `memory_gap_hook`              | enforcement | **disabled**             |\n| `product_spec_critique_nudge`  | enforcement | **disabled**             |\n\n- **Asymmetry (by design):** a missing *telemetry* key defaults ON; a missing\n  *enforcement* key defaults OFF — a blocking hook must never be fallback-enabled.\n  An explicit `true`\u002F`false` always wins. Set a key `false` to no-op that hook on\n  its next invocation (each hook is a fresh process).\n- **Enabling enforcement:** `product-spec\u002Finstall.sh --memory-hook` and\n  `product-spec-critique\u002Finstall.sh --critique-hook` flip the respective key to\n  `true`. The hooks are already wired into Stop by the bundle installer; the flag\n  is what activates them.\n- **`mark_bash_start` ⇒ `ms`:** keep it enabled for per-script wall-clock `ms`\n  (and the health lens's `avg_ms`). Disabled → the health lens degrades `avg_ms`\n  to `—` (no crash).\n- **Global kill-switch:** `CK_TELEMETRY_DISABLED=1` disables all telemetry hooks\n  regardless of config (enforcement hooks are unaffected by it).\n- **Crash log:** a swallowed hook exception leaves one line in\n  `.claude\u002Fhooks\u002F.logs\u002Fhook-crashes.log` (UTC ts, hook, exception type\u002Fmessage —\n  never the stdin payload). Always-on; disable with `CK_HOOK_AUDIT_DISABLED=1`.\n  The log is gitignored and excluded from the bundle.\n\n## Boundaries\n\n- **Read-only.** No edits to spec\u002Fcode\u002Fcatalog\u002Fmemory; no network; venv-run.\n- **GATE-NEVER-ASSUME \u002F GATE-NO-SILENT-REVERSAL:** not applicable in the usual sense (nothing is written\u002Fapproved), but the skill still never fabricates a metric — an absent signal is reported as absent.\n- **Deferred capabilities** (NOT in this skill): rich crash-log `errors.jsonl` (can't instrument shipped scripts), HTML output, and market-outcome measurement (PO-declared outcome tracking lives in `product-spec --learn`, offline; true market effectiveness stays out of scope). See `BACKLOG.md`.\n\n## CHANGELOG\n\nSee `CHANGELOG.md`.\n","# cleanmatic:telemetry — Usage & Health (Mức dùng & Sức khỏe)\n\nA **read-only** skill that tells the product owner, **in plain Vietnamese**, three things about their own tooling:\n\n1. **Mức dùng (Usage)** — which skills get used (and how often), token weight per skill, and which skills are never touched.\n2. **Sức khỏe (Health)** — which scripts error or run slow (approx), whether subagents succeed\u002Ffail, whether memory is tidy.\n3. **Một tín hiệu chất lượng nội bộ (a thin internal-quality proxy)** — after a `product-spec` run, did `validate` pass.\n\n**Honest framing — this is \"mức dùng & sức khỏe\", NOT \"hiệu quả\".** It measures *whether the machinery runs*, never *whether the product wins in the market*. (Product-outcome tracking shipped separately as `product-spec --learn`, but even that records PO-declared outcomes vs goals offline — still NOT a market-effectiveness metric.) The narration MUST keep that line bright (see the honesty gate below).\n\n## What this is NOT\n\n- **Not** a market\u002Fuser-outcome metric. The validate proxy = \"spec is well-formed\", not \"users adopted it\". (PO-declared outcome tracking lives in `product-spec --learn`; this skill does not read it.)\n- **Not** a writer — it never edits specs, code, the catalog, or memory. No `--apply`, no fixes.\n- **Not** billing-exact — token attribution and `ms` durations are **directional\u002Fapprox**.\n- **Not** a CI gate — opinion-free numbers for the PO to read, nothing blocks on it.\n\n## How it runs (deterministic gather → LLM narrates)\n\nThe split both repos follow: a **script gathers** (deterministic, never judges), the **skill narrates** (judges, in VI). The skill NEVER recomputes a number — it narrates the script's dict.\n\n```bash\n# Recipient bundle: system python3 with PyYAML (the bundle's single runtime dep, shipped via product-spec).\npython3 .\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Fanalyze_telemetry.py \\\n  --lens all --format ascii [--days 30] [--top 10]\n# In the cleanmatic dev repo, use the shared venv: .\u002F.claude\u002Fskills\u002F.venv\u002Fbin\u002Fpython3 …\n```\n\nDefault behaviour when the PO invokes `\u002Fcleanmatic:telemetry`:\n1. Run `analyze_telemetry.py --lens all --format ascii`.\n2. Read the aggregates; **narrate in Vietnamese** (default). Switch to English with `--lang en` (the script also localizes its fixed labels) or just \"in English\".\n3. Lead with the honesty gate; recommendations are **gợi ý (suggestions)** only.\n\nPass-through flags: `--lens \u003Cname>`, `--format md|mermaid|json`, `--days N`, `--top N`, `--lang vi|en` (fixed-label language, vi default), `--session \u003Cid>` \u002F `--all-sessions` (forensics). Runs under system `python3`; needs PyYAML (the bundle's single runtime dependency, shipped with product-spec).\n\n## Lenses\n\n| `--lens`     | Reads (sink)                          | Surfaces |\n|--------------|---------------------------------------|----------|\n| `usage`      | `invocations.jsonl` + transcripts     | invocation counts, per-skill tokens (approx), never-used catalog |\n| `session`    | `sessions.jsonl`                      | session count, avg\u002Fmedian duration, files, subagents, skill co-occurrence |\n| `health`     | `hook-telemetry.jsonl`                | per-script runs\u002Ferrors\u002Ferror-rate + avg `ms` (approx) |\n| `reliability`| `subagent-outcomes.jsonl`             | subagent success \u002F api_error \u002F timeout \u002F blocked \u002F unknown per type |\n| `workflow`   | `invocations.jsonl` + `data\u002Fskill-chains.yaml` | actual skill chains vs declared chains; deviations |\n| `validate`   | `last_validated.json` + `hook-telemetry` | validate-pass proxy (internal quality, NOT market outcome) |\n| `memory`     | `~\u002F.claude\u002Fprojects\u002F\u003Croot>\u002Fmemory\u002F`   | orphans, dead index entries, broken `[[links]]`, staleness (read-only) |\n| `product_memory` | `docs\u002Fproduct\u002F.memory\u002F`           | spec-store health: last-validated age, missing state files, critique-cache size (read-only) |\n| `artifact_heat` | `artifact-events.jsonl`            | artifact-edit frequency: most-edited spec artifacts (heat ranking), within `--days` window |\n| `forensics`  | session transcript JSONL              | one session reconstructed (skills\u002Ftools\u002Ftokens\u002Ffiles\u002Fduration) |\n| `all`        | the above (minus forensics)           | the dashboard-lite the PO reads first |\n\n## Low-volume gate (chưa đủ dữ liệu)\n\nBelow ~5 data points a lens shows raw counts + **\"chưa đủ dữ liệu\"** and **suppresses recommendations**. On a thin\u002Fnew repo most lenses WILL be gated — say so plainly; do not invent trends.\n\n## Narration & honesty gate (mandatory)\n\nDetailed rubric: `references\u002Fnarration-contract.md`. The non-negotiable parts:\n\n- **Separate MEASURED from NOT-MEASURED.** Every report MUST end with a section **\"Cái này KHÔNG đo được\"** naming at minimum: market\u002Fuser outcome (this skill measures usage\u002Fhealth, not market effectiveness); plus any lens that is empty\u002Fgated on current data → call it \"chưa đủ dữ liệu\", never spin it.\n- **Approx is approx.** Token weight, `ms`, and `exit` are inferred\u002Fdirectional — say \"ước lượng\", never present them as exact.\n- **Suggestions, not verdicts.** Phrase any action as a gợi ý the PO may ignore; the skill has no authority to prune skills, edit memory, or change scope.\n- **VI is native-quality** — correct diacritics, natural register for a non-technical owner; numbers stay numbers, skill ids stay ascii.\n\n## Hook config & crash log\n\nThe 7 project Python hooks (5 telemetry + 2 enforcement) share one runtime,\n`.claude\u002Fhooks\u002Fhook_runtime.py`, and one per-hook on\u002Foff file,\n`.claude\u002Fhooks\u002Fproduct-spec-hooks.json` (key = the hook's filename stem):\n\n| Hook stem (key)                | Kind        | Default when key missing |\n|--------------------------------|-------------|--------------------------|\n| `mark_bash_start`              | telemetry   | **enabled**              |\n| `track_skill_invocation`       | telemetry   | **enabled** (one key gates BOTH its registrations: PreToolUse:Skill + UserPromptExpansion) |\n| `track_script_execution`       | telemetry   | **enabled**              |\n| `track_subagent_outcome`       | telemetry   | **enabled**              |\n| `emit_session_summary`         | telemetry   | **enabled**              |\n| `memory_gap_hook`              | enforcement | **disabled**             |\n| `product_spec_critique_nudge`  | enforcement | **disabled**             |\n\n- **Asymmetry (by design):** a missing *telemetry* key defaults ON; a missing\n  *enforcement* key defaults OFF — a blocking hook must never be fallback-enabled.\n  An explicit `true`\u002F`false` always wins. Set a key `false` to no-op that hook on\n  its next invocation (each hook is a fresh process).\n- **Enabling enforcement:** `product-spec\u002Finstall.sh --memory-hook` and\n  `product-spec-critique\u002Finstall.sh --critique-hook` flip the respective key to\n  `true`. The hooks are already wired into Stop by the bundle installer; the flag\n  is what activates them.\n- **`mark_bash_start` ⇒ `ms`:** keep it enabled for per-script wall-clock `ms`\n  (and the health lens's `avg_ms`). Disabled → the health lens degrades `avg_ms`\n  to `—` (no crash).\n- **Global kill-switch:** `CK_TELEMETRY_DISABLED=1` disables all telemetry hooks\n  regardless of config (enforcement hooks are unaffected by it).\n- **Crash log:** a swallowed hook exception leaves one line in\n  `.claude\u002Fhooks\u002F.logs\u002Fhook-crashes.log` (UTC ts, hook, exception type\u002Fmessage —\n  never the stdin payload). Always-on; disable with `CK_HOOK_AUDIT_DISABLED=1`.\n  The log is gitignored and excluded from the bundle.\n\n## Boundaries\n\n- **Read-only.** No edits to spec\u002Fcode\u002Fcatalog\u002Fmemory; no network; venv-run.\n- **GATE-NEVER-ASSUME \u002F GATE-NO-SILENT-REVERSAL:** not applicable in the usual sense (nothing is written\u002Fapproved), but the skill still never fabricates a metric — an absent signal is reported as absent.\n- **Deferred capabilities** (NOT in this skill): rich crash-log `errors.jsonl` (can't instrument shipped scripts), HTML output, and market-outcome measurement (PO-declared outcome tracking lives in `product-spec --learn`, offline; true market effectiveness stays out of scope). See `BACKLOG.md`.\n\n## CHANGELOG\n\nSee `CHANGELOG.md`.\n",{"name":5,"category":24,"keywords":25,"metadata":39,"description":7,"when_to_use":42,"argument-hint":43,"user-invocable":44},"observability",[26,27,28,29,30,31,32,33,34,35,36,37,38],"telemetry","usage","health","skills","tokens","sessions","reliability","subagents","memory","validate","vietnamese","dashboard","analytics",{"author":40,"version":41},"cleanmatic","1.1.1","When the (non-technical) product owner asks how their skills are being used, which scripts error or run slow, whether subagents succeed, whether memory is tidy, or whether the last spec validate passed — and wants it explained in plain Vietnamese, not raw logs.","[--lens usage|session|health|reliability|workflow|validate|memory|product_memory|artifact_heat|forensics|all] [--format ascii|md|mermaid|json] [--days N] [--top N] [--lang vi|en]",true,"master","b67b7fe83c89b23de6fdd66e1386dda1e9ed1de3",".claude\u002Fskills\u002Ftelemetry",9,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec","https:\u002F\u002Fgithub.com\u002Fhieubui2409","7+ yrs lead architect building high-perf distributed backend systems (Java\u002FGo\u002FPython). Expert in Microservices, Enterprise AI Mesh, A2A & MCP protocols.","2026-07-21 01:36:59",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":44},[55,58,61],{"tool":56,"command":57},"npx","npx skills add hieubui2409\u002Fproduct-spec --skill \"cleanmatic:telemetry\"",{"tool":59,"command":60},"bunx","bunx skills add hieubui2409\u002Fproduct-spec --skill \"cleanmatic:telemetry\"",{"tool":62,"command":63},"pnpm","pnpm dlx skills add hieubui2409\u002Fproduct-spec --skill \"cleanmatic:telemetry\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002FSKILL.md",[66,72,76,80,84,88,92,98,102,106,110,114,118,122,126,130,134,138,142,146,150,154,158,162,166,170,174,178,182,186,190,194,198,202,206,210,214,218,222,226,230,234,238,242,246,250,254,258,262,266,270,274,278],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"CHANGELOG.md","REFERENCE","参考文档",5465,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002FCHANGELOG.md",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"data\u002Fskill-chains.yaml",1183,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fdata\u002Fskill-chains.yaml",{"path":77,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":78,"sourceHtmlUrl":79},"GUIDE-EN.md",16174,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002FGUIDE-EN.md",{"path":81,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":82,"sourceHtmlUrl":83},"GUIDE-VI.md",17653,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002FGUIDE-VI.md",{"path":85,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":86,"sourceHtmlUrl":87},"README.md",17452,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002FREADME.md",{"path":89,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fnarration-contract.md",3792,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Freferences\u002Fnarration-contract.md",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fanalyze_telemetry.py","SCRIPT","脚本",7773,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Fanalyze_telemetry.py",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Fcatalog.py",4135,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Fcatalog.py",{"path":103,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fformatters.py",3334,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Fformatters.py",{"path":107,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fharvester.py",6035,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Fharvester.py",{"path":111,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Flens_artifact_heat.py",2471,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_artifact_heat.py",{"path":115,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":116,"sourceHtmlUrl":117},"scripts\u002Flens_forensics.py",3899,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_forensics.py",{"path":119,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":120,"sourceHtmlUrl":121},"scripts\u002Flens_health.py",2174,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_health.py",{"path":123,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Flens_memory_health.py",5518,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_memory_health.py",{"path":127,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":128,"sourceHtmlUrl":129},"scripts\u002Flens_product_memory.py",3652,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_product_memory.py",{"path":131,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":132,"sourceHtmlUrl":133},"scripts\u002Flens_reliability.py",2273,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_reliability.py",{"path":135,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":136,"sourceHtmlUrl":137},"scripts\u002Flens_session_shape.py",2104,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_session_shape.py",{"path":139,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":140,"sourceHtmlUrl":141},"scripts\u002Flens_usage_tokens.py",5660,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_usage_tokens.py",{"path":143,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":144,"sourceHtmlUrl":145},"scripts\u002Flens_validate_proxy.py",3876,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_validate_proxy.py",{"path":147,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":148,"sourceHtmlUrl":149},"scripts\u002Flens_workflow_chains.py",5251,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Flens_workflow_chains.py",{"path":151,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":152,"sourceHtmlUrl":153},"scripts\u002Fregister_telemetry_hooks.py",11366,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Fregister_telemetry_hooks.py",{"path":155,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":156,"sourceHtmlUrl":157},"scripts\u002Ftelemetry_paths.py",9673,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftelemetry_paths.py",{"path":159,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":160,"sourceHtmlUrl":161},"scripts\u002Ftelemetry_render.py",29949,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftelemetry_render.py",{"path":163,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":164,"sourceHtmlUrl":165},"scripts\u002Ftests\u002Ffixtures\u002Fmemory\u002Fgood-fact.md",222,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Fmemory\u002Fgood-fact.md",{"path":167,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":168,"sourceHtmlUrl":169},"scripts\u002Ftests\u002Ffixtures\u002Fmemory\u002FMEMORY.md",164,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Fmemory\u002FMEMORY.md",{"path":171,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":172,"sourceHtmlUrl":173},"scripts\u002Ftests\u002Ffixtures\u002Fmemory\u002Forphan-fact.md",204,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Fmemory\u002Forphan-fact.md",{"path":175,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":176,"sourceHtmlUrl":177},"scripts\u002Ftests\u002Ffixtures\u002Fsessions\u002FsessB.jsonl",839,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Fsessions\u002FsessB.jsonl",{"path":179,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":180,"sourceHtmlUrl":181},"scripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Fhook-telemetry.jsonl",493,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Fhook-telemetry.jsonl",{"path":183,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":184,"sourceHtmlUrl":185},"scripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Finvocations.jsonl",591,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Finvocations.jsonl",{"path":187,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":188,"sourceHtmlUrl":189},"scripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Fsessions.jsonl",420,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Fsessions.jsonl",{"path":191,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":192,"sourceHtmlUrl":193},"scripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Fsubagent-outcomes.jsonl",321,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Fsubagent-outcomes.jsonl",{"path":195,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":196,"sourceHtmlUrl":197},"scripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Funknown-stray.jsonl",93,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Ftelemetry\u002Funknown-stray.jsonl",{"path":199,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":200,"sourceHtmlUrl":201},"scripts\u002Ftests\u002Ftest_analyze_telemetry_cli.py",8943,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_analyze_telemetry_cli.py",{"path":203,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":204,"sourceHtmlUrl":205},"scripts\u002Ftests\u002Ftest_catalog.py",2630,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_catalog.py",{"path":207,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":208,"sourceHtmlUrl":209},"scripts\u002Ftests\u002Ftest_fixtures_sane.py",2606,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_fixtures_sane.py",{"path":211,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":212,"sourceHtmlUrl":213},"scripts\u002Ftests\u002Ftest_formatters.py",2389,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_formatters.py",{"path":215,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":216,"sourceHtmlUrl":217},"scripts\u002Ftests\u002Ftest_harvester.py",12136,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_harvester.py",{"path":219,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":220,"sourceHtmlUrl":221},"scripts\u002Ftests\u002Ftest_lens_artifact_heat.py",6305,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_artifact_heat.py",{"path":223,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":224,"sourceHtmlUrl":225},"scripts\u002Ftests\u002Ftest_lens_forensics.py",1501,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_forensics.py",{"path":227,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":228,"sourceHtmlUrl":229},"scripts\u002Ftests\u002Ftest_lens_health.py",2022,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_health.py",{"path":231,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":232,"sourceHtmlUrl":233},"scripts\u002Ftests\u002Ftest_lens_memory_health.py",2318,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_memory_health.py",{"path":235,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":236,"sourceHtmlUrl":237},"scripts\u002Ftests\u002Ftest_lens_product_memory.py",3576,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_product_memory.py",{"path":239,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":240,"sourceHtmlUrl":241},"scripts\u002Ftests\u002Ftest_lens_reliability.py",1539,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_reliability.py",{"path":243,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":244,"sourceHtmlUrl":245},"scripts\u002Ftests\u002Ftest_lens_session_shape.py",1697,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_session_shape.py",{"path":247,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":248,"sourceHtmlUrl":249},"scripts\u002Ftests\u002Ftest_lens_usage_tokens.py",3557,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_usage_tokens.py",{"path":251,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":252,"sourceHtmlUrl":253},"scripts\u002Ftests\u002Ftest_lens_validate_proxy.py",3840,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_validate_proxy.py",{"path":255,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":256,"sourceHtmlUrl":257},"scripts\u002Ftests\u002Ftest_lens_workflow_chains.py",3767,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_lens_workflow_chains.py",{"path":259,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":260,"sourceHtmlUrl":261},"scripts\u002Ftests\u002Ftest_low_volume_gate.py",1016,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_low_volume_gate.py",{"path":263,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":264,"sourceHtmlUrl":265},"scripts\u002Ftests\u002Ftest_register_new_hooks.py",4963,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_register_new_hooks.py",{"path":267,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":268,"sourceHtmlUrl":269},"scripts\u002Ftests\u002Ftest_register_telemetry_hooks.py",10166,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_register_telemetry_hooks.py",{"path":271,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":272,"sourceHtmlUrl":273},"scripts\u002Ftests\u002Ftest_telemetry_paths_helpers.py",2676,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_telemetry_paths_helpers.py",{"path":275,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":276,"sourceHtmlUrl":277},"scripts\u002Ftests\u002Ftest_telemetry_paths.py",9323,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_telemetry_paths.py",{"path":279,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":280,"sourceHtmlUrl":281},"scripts\u002Ftests\u002Ftest_telemetry_render.py",6949,"https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ftest_telemetry_render.py",[283,289,295,301,307,313],{"skillNo":284,"name":5,"nameZh":6,"description":285,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":286,"categories":287,"keywords":288,"publishedAt":19},"01M7540TZGQKF7NV8B23PAY4FD","x","https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Fskills\u002Ftelemetry\u002FSKILL.md",[],[],{"skillNo":290,"name":291,"nameZh":6,"description":285,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":292,"categories":293,"keywords":294,"publishedAt":19},"01M7540T3DZG1QX26JX35RJ8CS","cleanmatic:release","https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Fskills\u002Frelease\u002FSKILL.md",[],[],{"skillNo":296,"name":297,"nameZh":6,"description":285,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":298,"categories":299,"keywords":300,"publishedAt":19},"01M7540S4Z2A6PRTAZ8SGC8VHS","cleanmatic:product-spec","https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Fskills\u002Fproduct-spec\u002FSKILL.md",[],[],{"skillNo":302,"name":303,"nameZh":6,"description":285,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":304,"categories":305,"keywords":306,"publishedAt":19},"01M7540PPNZ14MCGHSC98QBK5V","cleanmatic:product-spec-critique","https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelemetry\u002Fscripts\u002Ftests\u002Ffixtures\u002Fskills\u002Fproduct-spec-critique\u002FSKILL.md",[],[],{"skillNo":308,"name":291,"nameZh":6,"description":309,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":310,"categories":311,"keywords":312,"publishedAt":19},"01M754061DBWYP0GSD7ZMV62CH","Cut a versioned release of the product-spec bundle: pack opt-in .claude\u002F artifacts into a deterministic tar.gz AND manage the root CHANGELOG.md release lifecycle (lock [Unreleased] → [X.Y.Z], bump manifest, hand the owner the tag push that fires release CI). Manifest-first selection; multiplatform recipient installer.","https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Frelease\u002FSKILL.md",[],[],{"skillNo":314,"name":297,"nameZh":6,"description":315,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":316,"categories":317,"keywords":318,"publishedAt":19},"01M753ZW1QFVGTJ6EQ689TEAX4","Interview-driven product spec hierarchy (Vision\u002FBRD\u002FPRD\u002FEpic\u002FStory) with traceability, validation, and visualization for product owners. Use when a non-technical PO needs to capture, structure, validate, or visualize product requirements without writing code.","https:\u002F\u002Fgithub.com\u002Fhieubui2409\u002Fproduct-spec\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fproduct-spec\u002FSKILL.md",[],[]]