[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CTGRN8Y6VCFDK8656XFF1N":3,"skill-same:01M7CTGRN8Y6VCFDK8656XFF1N":51},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CTGRN8Y6VCFDK8656XFF1N","artifact-logging",null,"Procedures for logging observations, decisions, and discoveries during agent work. Load when you need to write or read logs, create ADRs, or understand logging conventions.","xiaden\u002FSkyScow","xiaden","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3605480?v=4","01M7CTGKNTD1XNQE710J977HVD","Lucian Hardy","01M7CTGKPVQ3XRNXNRJ3A6E31F",1,"MIT","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fartifact-logging\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: artifact-logging\ndescription: Procedures for logging observations, decisions, and discoveries during agent work. Load when you need to write or read logs, create ADRs, or understand logging conventions.\n---\n\n# Artifact Logging\n\n**Purpose:** Procedures and conventions for logging observations, decisions, and discoveries during agent work. Covers log writing, log reading, ADR proposal\u002Fapproval\u002Fcommit, and access rules. Committed governance records live in the workspace-local `architecture-decisions` and `system-requirements` skills.\n\n## When to Use\n\n**Trigger conditions:**\n- Writing or reading agent log entries (`log_write`, `log_read`)\n- Creating or committing Architecture Decision Records (`adr_suggest`, `adr_commit`)\n- Understanding log access rules across agent hierarchies\n- Following logging conventions during Change DAG execution\n\n**Do NOT use this skill for:**\n- Creating design documents (use `dd_create`)\n- Writing ASR records (use `asr_create`; committed records live in the `system-requirements` skill)\n- Managing Change DAGs (use `dag_*` tools)\n\n## Governance Locations\n\nCommitted governance records are workspace-local skill content, not a fixed repository directory. This skill owns the **proposal, approval, and commit workflow** for them:\n\n- **ADRs** commit into the `architecture-decisions` skill's status directories (`references\u002F{accepted,deprecated,superseded}\u002F`) and are indexed by its generated `SKILL.md`. The two-step `adr_suggest` → `adr_commit` workflow below owns proposal and user approval; `adr_read(name)` reads one committed record by identity.\n- **ASRs** commit into the `system-requirements` skill's status directories (`references\u002F{active,archived,superseded}\u002F`) and are indexed by its generated `SKILL.md`; `asr_create` writes one and `asr_read(name)` reads it by identity.\n\nThese skills are workspace-local capability: their existence means the repository has that governance corpus, and their absence means it does not. Do not create empty governance skills.\n\n## When to Log\n\nLog durable knowledge only — entries a future agent (including yourself in later sessions) cannot cheaply recover from the current code, Change DAG\u002FDD, or current external evidence. Logging is for memory, not ceremony: do not log routine progress, obvious observations, successful ordinary commands, trivially rediscoverable facts, or ceremonial status entries.\n\n| Observable fact | Category | Example |\n|-----------------|----------|---------|\n| An architectural or design decision was made | `decision` | \"Used component-level caching over service-level — keeps DI simpler\" |\n| Work is blocked | `blocker` | \"Upstream contract missing — cannot proceed\" |\n| Important uncertainty remains unresolved | `observation` + tag `uncertainty` | \"Unclear if this migration needs a down path — proceeding without\" |\n| Work deviated from an accepted Change DAG or DD | `observation` + tag `dag-deviation` | Record the drift and its reason |\n| A non-obvious codebase fact was discovered | `discovery` | \"AQL UPSERT requires all three clauses even when update is empty\" |\n| An approach was proven to fail | `dead-end` | \"Tried using rename on re-exported symbol — doesn't follow re-exports\" |\n| Important external evidence was found | `research` | \"Library scan workflow depends on filesystem watcher, not polling\" |\n| A risk is left unresolved | `observation` + tag `risk` | Record the unresolved risk and its trigger |\n\n## Log Entry Format\n\n```python\nlog_write(\n    agent=\"your-agent-name\",  # e.g., \"nyx\", \"qa-reviewer\"\n    category=\"observation\",   # or \"discovery\", \"decision\", \"dead-end\", \"research\", \"blocker\"\n    message=\"Clear description of what happened\",\n    tags=[\"dag-slug\", \"module-name\"]  # Required for durable entries: at least one tag\n)\n```\n\n**Always include:**\n- `agent`: Your agent name (e.g., \"nyx\", \"rnd-dd-author\")\n- `category`: One of the categories above\n- `message`: Clear, specific description\n- `tags`: At least one tag for durable entries — a Change DAG slug (e.g., \"myfeature-change\"), module name, or topic. The `log_write` schema may accept an empty list, but policy requires at least one tag on every durable entry so future agents can find it.\n\n**Often include:**\n- Additional `tags` beyond the first — more context improves discoverability (at least one is required; more is often useful)\n\n## Reading Logs\n\nBefore starting work, check for relevant context:\n\n```python\n# Check for prior observations about this module\u002Farea\nlog_read(agent=\"your-agent-name\", tag=\"module-name\")\n\n# Check for logs from a specific Change DAG\nlog_read(tag=\"dag-slug\")\n\n# Check for specific categories\nlog_read(category=\"discovery\")\nlog_read(category=\"dead-end\")\n\n# Reconstruct execution history (for managers picking up mid-stream)\nlog_read(since=\"\u003Ctimestamp>\")  # All logs since a time\nlog_read(tag=\"\u003Cdag-slug>\")   # All logs for a Change DAG\n```\n\n## ADR Workflow\n\nWhen you make a decision that constrains future work:\n\n1. **Log the reasoning first** using `log_write` with category `decision`\n2. **Create the ADR** using `adr_suggest` — reference the log entry in `source_log`\n3. **User approves** (you must ask)\n4. **Commit the ADR** using `adr_commit` — the committed record lands in the `architecture-decisions` skill\n\n**When to create ADRs:**\n- Architectural decisions that constrain future work\n- Choosing between approaches with significant tradeoffs\n- Changes to public APIs or contracts\n- Breaking a previous ADR (supersede it, don't silently ignore)\n\n**When NOT to create ADRs:**\n- Implementation details (those go in design docs)\n- One-off fixes (those go in logs)\n- Trivial choices (just log them)\n\n## Log Access Rules\n\nAgents can read logs from:\n- **Own logs**: Your own agent name\n- **Up**: Agents that manage you (e.g., a manager can read logs of agents it dispatches)\n- **Down**: Agents you manage (e.g., a manager can read its dispatched agents' logs)\n- **Audit targets**: Specific agents you're responsible for reviewing\n\nAgents **cannot** read logs from:\n- Peer agents (unless explicitly allowed)\n- Agents in unrelated departments\n\n## References\n\n- [**`references\u002Flogging-patterns.md`**](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fartifact-logging\u002Freferences\u002Flogging-patterns.md) — Detailed patterns: Change DAG tag requirements, mid-stream context recovery, discovery logging, dead-end logging\n\n\n## Process-Artifact Lifecycle\n\nDD adversarial logs live as root-level `ADVERSARIAL.md` files inside each `artifacts\u002Fdesigns\u002Fpending\u002F{slug}\u002F` or `artifacts\u002Fdesigns\u002Fcompleted\u002F{slug}\u002F` bundle. Bundle artifacts record their owner, status, and disposition; completed bundles move to `artifacts\u002Fdesigns\u002Fcompleted\u002F{slug}\u002F` or are explicitly deprecated. Large adversarial logs must declare a retention period or an archive\u002Fdeprecate disposition.\n\nWhen a Change DAG or DD is superseded, update only its `Status` field according to the ADR\u002Fsupersession convention, add a back-pointer to the superseding artifact, and remove it from the executable set. Mark stale handoffs superseded when their contract is superseded.\n","# Artifact Logging\n\n**Purpose:** Procedures and conventions for logging observations, decisions, and discoveries during agent work. Covers log writing, log reading, ADR proposal\u002Fapproval\u002Fcommit, and access rules. Committed governance records live in the workspace-local `architecture-decisions` and `system-requirements` skills.\n\n## When to Use\n\n**Trigger conditions:**\n- Writing or reading agent log entries (`log_write`, `log_read`)\n- Creating or committing Architecture Decision Records (`adr_suggest`, `adr_commit`)\n- Understanding log access rules across agent hierarchies\n- Following logging conventions during Change DAG execution\n\n**Do NOT use this skill for:**\n- Creating design documents (use `dd_create`)\n- Writing ASR records (use `asr_create`; committed records live in the `system-requirements` skill)\n- Managing Change DAGs (use `dag_*` tools)\n\n## Governance Locations\n\nCommitted governance records are workspace-local skill content, not a fixed repository directory. This skill owns the **proposal, approval, and commit workflow** for them:\n\n- **ADRs** commit into the `architecture-decisions` skill's status directories (`references\u002F{accepted,deprecated,superseded}\u002F`) and are indexed by its generated `SKILL.md`. The two-step `adr_suggest` → `adr_commit` workflow below owns proposal and user approval; `adr_read(name)` reads one committed record by identity.\n- **ASRs** commit into the `system-requirements` skill's status directories (`references\u002F{active,archived,superseded}\u002F`) and are indexed by its generated `SKILL.md`; `asr_create` writes one and `asr_read(name)` reads it by identity.\n\nThese skills are workspace-local capability: their existence means the repository has that governance corpus, and their absence means it does not. Do not create empty governance skills.\n\n## When to Log\n\nLog durable knowledge only — entries a future agent (including yourself in later sessions) cannot cheaply recover from the current code, Change DAG\u002FDD, or current external evidence. Logging is for memory, not ceremony: do not log routine progress, obvious observations, successful ordinary commands, trivially rediscoverable facts, or ceremonial status entries.\n\n| Observable fact | Category | Example |\n|-----------------|----------|---------|\n| An architectural or design decision was made | `decision` | \"Used component-level caching over service-level — keeps DI simpler\" |\n| Work is blocked | `blocker` | \"Upstream contract missing — cannot proceed\" |\n| Important uncertainty remains unresolved | `observation` + tag `uncertainty` | \"Unclear if this migration needs a down path — proceeding without\" |\n| Work deviated from an accepted Change DAG or DD | `observation` + tag `dag-deviation` | Record the drift and its reason |\n| A non-obvious codebase fact was discovered | `discovery` | \"AQL UPSERT requires all three clauses even when update is empty\" |\n| An approach was proven to fail | `dead-end` | \"Tried using rename on re-exported symbol — doesn't follow re-exports\" |\n| Important external evidence was found | `research` | \"Library scan workflow depends on filesystem watcher, not polling\" |\n| A risk is left unresolved | `observation` + tag `risk` | Record the unresolved risk and its trigger |\n\n## Log Entry Format\n\n```python\nlog_write(\n    agent=\"your-agent-name\",  # e.g., \"nyx\", \"qa-reviewer\"\n    category=\"observation\",   # or \"discovery\", \"decision\", \"dead-end\", \"research\", \"blocker\"\n    message=\"Clear description of what happened\",\n    tags=[\"dag-slug\", \"module-name\"]  # Required for durable entries: at least one tag\n)\n```\n\n**Always include:**\n- `agent`: Your agent name (e.g., \"nyx\", \"rnd-dd-author\")\n- `category`: One of the categories above\n- `message`: Clear, specific description\n- `tags`: At least one tag for durable entries — a Change DAG slug (e.g., \"myfeature-change\"), module name, or topic. The `log_write` schema may accept an empty list, but policy requires at least one tag on every durable entry so future agents can find it.\n\n**Often include:**\n- Additional `tags` beyond the first — more context improves discoverability (at least one is required; more is often useful)\n\n## Reading Logs\n\nBefore starting work, check for relevant context:\n\n```python\n# Check for prior observations about this module\u002Farea\nlog_read(agent=\"your-agent-name\", tag=\"module-name\")\n\n# Check for logs from a specific Change DAG\nlog_read(tag=\"dag-slug\")\n\n# Check for specific categories\nlog_read(category=\"discovery\")\nlog_read(category=\"dead-end\")\n\n# Reconstruct execution history (for managers picking up mid-stream)\nlog_read(since=\"\u003Ctimestamp>\")  # All logs since a time\nlog_read(tag=\"\u003Cdag-slug>\")   # All logs for a Change DAG\n```\n\n## ADR Workflow\n\nWhen you make a decision that constrains future work:\n\n1. **Log the reasoning first** using `log_write` with category `decision`\n2. **Create the ADR** using `adr_suggest` — reference the log entry in `source_log`\n3. **User approves** (you must ask)\n4. **Commit the ADR** using `adr_commit` — the committed record lands in the `architecture-decisions` skill\n\n**When to create ADRs:**\n- Architectural decisions that constrain future work\n- Choosing between approaches with significant tradeoffs\n- Changes to public APIs or contracts\n- Breaking a previous ADR (supersede it, don't silently ignore)\n\n**When NOT to create ADRs:**\n- Implementation details (those go in design docs)\n- One-off fixes (those go in logs)\n- Trivial choices (just log them)\n\n## Log Access Rules\n\nAgents can read logs from:\n- **Own logs**: Your own agent name\n- **Up**: Agents that manage you (e.g., a manager can read logs of agents it dispatches)\n- **Down**: Agents you manage (e.g., a manager can read its dispatched agents' logs)\n- **Audit targets**: Specific agents you're responsible for reviewing\n\nAgents **cannot** read logs from:\n- Peer agents (unless explicitly allowed)\n- Agents in unrelated departments\n\n## References\n\n- [**`references\u002Flogging-patterns.md`**](file:\u002F\u002F\u002Fhome\u002Fopencode\u002F.config\u002Fopencode\u002Fskills\u002Fartifact-logging\u002Freferences\u002Flogging-patterns.md) — Detailed patterns: Change DAG tag requirements, mid-stream context recovery, discovery logging, dead-end logging\n\n\n## Process-Artifact Lifecycle\n\nDD adversarial logs live as root-level `ADVERSARIAL.md` files inside each `artifacts\u002Fdesigns\u002Fpending\u002F{slug}\u002F` or `artifacts\u002Fdesigns\u002Fcompleted\u002F{slug}\u002F` bundle. Bundle artifacts record their owner, status, and disposition; completed bundles move to `artifacts\u002Fdesigns\u002Fcompleted\u002F{slug}\u002F` or are explicitly deprecated. Large adversarial logs must declare a retention period or an archive\u002Fdeprecate disposition.\n\nWhen a Change DAG or DD is superseded, update only its `Status` field according to the ADR\u002Fsupersession convention, add a back-pointer to the superseding artifact, and remove it from the executable set. Mark stale handoffs superseded when their contract is superseded.\n",{"name":5,"description":7},"main","8f95d6b7cbf4ec39161b4e6c8bc5e1493e58003c","config\u002Fskills\u002Fartifact-logging",0,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow","https:\u002F\u002Fgithub.com\u002Fxiaden","2026-09-30 22:33:49",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add xiaden\u002FSkyScow --skill artifact-logging",{"tool":37,"command":38},"bunx","bunx skills add xiaden\u002FSkyScow --skill artifact-logging",{"tool":40,"command":41},"pnpm","pnpm dlx skills add xiaden\u002FSkyScow --skill artifact-logging","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fartifact-logging\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Flogging-patterns.md","REFERENCE","参考文档",1406,"https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fartifact-logging\u002Freferences\u002Flogging-patterns.md",[52,58,65,71,78,85],{"skillNo":53,"name":54,"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":55,"categories":56,"keywords":57,"publishedAt":19},"01M7CTNJ49PJ794TEFBCNYYKQM","unquoted-colon","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Funquoted-colon\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},"01M7CTNENFBZPEX63HNSRBCW4T","quoted-description","Use when a plain scalar contains a colon: like this one.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Fquoted-description\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"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":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CTNBBPKA6GMCVEM3GPB59F","block-description","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Ftools\u002Ftests\u002Ffixtures\u002Fskills\u002Fblock-description\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CTN4M0SR4Z4TPJMHWC3A3B","work-routing","Canonical authority for who owns the next unit of work — direct work versus delegation, task tiers, bounded localization, the Change DAG size threshold, R&D evaluation routing, progressive research escalation, researcher scope signals, and QA\u002Fsupport owner selection. Use before choosing execution, investigation, design, or QA ownership; do not use to construct dispatch prompts, handoff schemas, or Change DAG\u002FDD tool operation.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fwork-routing\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CTMY5AY3NSNHGQJA0M7VP9","update-docs","Update project documentation to match code changes — generate codemaps, refresh READMEs, detect doc\u002Fcode drift using AST analysis. Use when updating documentation after code changes, generating codemaps, verifying doc accuracy, or detecting stale documentation. Do NOT use for writing API reference docs from scratch (use doc-coauthoring) or for creating new skill files (use making-editing-skills).","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fupdate-docs\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CTMSQD82CPD53C6F07J0R9","skill-loading-system","Explain or troubleshoot OpenCode skill discovery, loading, permissions, availability, or prompt injection.","https:\u002F\u002Fgithub.com\u002Fxiaden\u002FSkyScow\u002Fblob\u002Fmain\u002Fconfig\u002Fskills\u002Fskill-loading-system\u002FSKILL.md",[],[]]