[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DK48KKWKRMQJ5F99ZFXPKA":3,"skill-same:01M7DK48KKWKRMQJ5F99ZFXPKA":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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7DK48KKWKRMQJ5F99ZFXPKA","dh-explore",null,"Explore codebases quickly using glob, grep, and targeted reads, and return compact evidence with exact file references. Use for codebase exploration, file search, pattern discovery, dependency mapping, or answering questions about where code lives — with the smallest search that can answer it.","andrescevp\u002Fdevelopment-harness","andrescevp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10025841?v=4","01M7DK1Q07H5GT5R4JSGMWV1DE","Andres Cevallos","01M7DK1Q18W9DHVMV4HZ4BQAY3",8,"MIT","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-explore\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dh-explore\ndescription: >\n  Explore codebases quickly using glob, grep, and targeted reads, and return\n  compact evidence with exact file references. Use for codebase exploration,\n  file search, pattern discovery, dependency mapping, or answering questions\n  about where code lives — with the smallest search that can answer it.\nlicense: MIT\ncompatibility: opencode, copilot, antigravity\nallowed-tools: read, glob, grep\nmetadata:\n  audience: developers\n  workflow: development\n---\n\nGather enough evidence to answer accurately while minimizing time, tokens, and\nunnecessary file access.\n\n## Core Rules\n\n- Start with the smallest search that can answer the question.\n- Prefer `glob`, `grep`, and targeted `read` calls over broad scans.\n- Batch independent searches and reads when possible.\n- Read only the specific files and sections needed to confirm the answer.\n- Ignore noisy or generated directories such as `node_modules`, `dist`,\n  `build`, `.git`, and cache\u002Foutput folders unless the caller explicitly asks\n  about them.\n- Stop exploring once the answer is supported by concrete evidence.\n\n## Code Graph First\n\nWhen `dh-setup` indexed the project, use the `dh-code-query` skill before\nbroad scans:\n\n- `cgr graph definition` \u002F `resolve` for exact symbols and locations.\n- `cgr graph callers` \u002F `callees` \u002F `importers` \u002F `implementors` for\n  relationships.\n- `cgr graph tests-reaching` for the tests that exercise a symbol.\n\nTreat graph rows as candidates and confirm them in the source. Fall back to\n`glob` \u002F `grep` when the project is not indexed, the graph is stale, or the\nquestion is textual rather than structural.\n\n## Search Order\n\n1. **Locate** — use `glob` to find candidate files by name or extension.\n2. **Narrow** — use `grep` to find the relevant symbols, strings, or patterns\n   inside those candidates (constrain with `include`\u002F`glob` filters when\n   available).\n3. **Confirm** — open only the matching files and the sections that prove the\n   answer with targeted `read` calls (offset\u002Flimit for large files).\n\nEscalate to broader scans only when the narrow search returns no usable\nevidence, and say why the broader scope is needed.\n\n## Efficiency Rules\n\n- Do not read entire large files unless the answer depends on full-file\n  context.\n- Do not scan unrelated directories just to be thorough.\n- Reuse previously gathered evidence instead of repeating searches.\n- Summarize findings clearly with exact file references (path and line when\n  available).\n- Separate confirmed facts from inferences; never present a guess as evidence.\n\n## Safety Rules\n\n- Respect least privilege at all times.\n- Do not attempt to read secrets, credentials, or sensitive config outside the\n  allowed workspace; never echo secret values.\n- Do not edit files, run destructive commands, or use network access unless\n  explicitly required.\n- If the requested scope is unclear, ask for the minimum clarification needed.\n\n## Output Format\n\n- Lead with the direct answer.\n- Follow with the evidence: exact file paths and line references.\n- Keep the summary compact — no full-file dumps, no irrelevant matches.\n- List open questions or missing evidence explicitly when the answer is\n  incomplete.\n\n## When to Use\n\n- A caller asks where something lives, how a flow works, or which files are\n  involved.\n- Planning or implementation needs codebase context before acting.\n- A search must distinguish the relevant code from generated or vendored\n  noise.\n\n## When Not to Use\n\n- Running commands, tests, builds, or validation — use `dh-execute-cli`.\n- Editing or fixing code — use the implementation workflow.\n- Reviewing a change — use `dh-code-review` \u002F `dh-review`.\n\n## Doc search\n\n**Documentation management:** delegate create \u002F update \u002F delete \u002F retrieve of generated documents (excluding docs\u002Fplans) to the best available documentation agent (bundled documentation capability as fallback) — the main and only documentation owner (see dh-create-documentation).\n\nSearch generated documentation quickly: `notesmd-cli search-content \"\u003Cterm>\" --vault \"\u003Cproject-name>\"` or `obsidian search query=\"\u003Cterm>\"` (fallback: `rg --glob '*.md' \"\u003Cterm>\" docs\u002F`).\n","Gather enough evidence to answer accurately while minimizing time, tokens, and\nunnecessary file access.\n\n## Core Rules\n\n- Start with the smallest search that can answer the question.\n- Prefer `glob`, `grep`, and targeted `read` calls over broad scans.\n- Batch independent searches and reads when possible.\n- Read only the specific files and sections needed to confirm the answer.\n- Ignore noisy or generated directories such as `node_modules`, `dist`,\n  `build`, `.git`, and cache\u002Foutput folders unless the caller explicitly asks\n  about them.\n- Stop exploring once the answer is supported by concrete evidence.\n\n## Code Graph First\n\nWhen `dh-setup` indexed the project, use the `dh-code-query` skill before\nbroad scans:\n\n- `cgr graph definition` \u002F `resolve` for exact symbols and locations.\n- `cgr graph callers` \u002F `callees` \u002F `importers` \u002F `implementors` for\n  relationships.\n- `cgr graph tests-reaching` for the tests that exercise a symbol.\n\nTreat graph rows as candidates and confirm them in the source. Fall back to\n`glob` \u002F `grep` when the project is not indexed, the graph is stale, or the\nquestion is textual rather than structural.\n\n## Search Order\n\n1. **Locate** — use `glob` to find candidate files by name or extension.\n2. **Narrow** — use `grep` to find the relevant symbols, strings, or patterns\n   inside those candidates (constrain with `include`\u002F`glob` filters when\n   available).\n3. **Confirm** — open only the matching files and the sections that prove the\n   answer with targeted `read` calls (offset\u002Flimit for large files).\n\nEscalate to broader scans only when the narrow search returns no usable\nevidence, and say why the broader scope is needed.\n\n## Efficiency Rules\n\n- Do not read entire large files unless the answer depends on full-file\n  context.\n- Do not scan unrelated directories just to be thorough.\n- Reuse previously gathered evidence instead of repeating searches.\n- Summarize findings clearly with exact file references (path and line when\n  available).\n- Separate confirmed facts from inferences; never present a guess as evidence.\n\n## Safety Rules\n\n- Respect least privilege at all times.\n- Do not attempt to read secrets, credentials, or sensitive config outside the\n  allowed workspace; never echo secret values.\n- Do not edit files, run destructive commands, or use network access unless\n  explicitly required.\n- If the requested scope is unclear, ask for the minimum clarification needed.\n\n## Output Format\n\n- Lead with the direct answer.\n- Follow with the evidence: exact file paths and line references.\n- Keep the summary compact — no full-file dumps, no irrelevant matches.\n- List open questions or missing evidence explicitly when the answer is\n  incomplete.\n\n## When to Use\n\n- A caller asks where something lives, how a flow works, or which files are\n  involved.\n- Planning or implementation needs codebase context before acting.\n- A search must distinguish the relevant code from generated or vendored\n  noise.\n\n## When Not to Use\n\n- Running commands, tests, builds, or validation — use `dh-execute-cli`.\n- Editing or fixing code — use the implementation workflow.\n- Reviewing a change — use `dh-code-review` \u002F `dh-review`.\n\n## Doc search\n\n**Documentation management:** delegate create \u002F update \u002F delete \u002F retrieve of generated documents (excluding docs\u002Fplans) to the best available documentation agent (bundled documentation capability as fallback) — the main and only documentation owner (see dh-create-documentation).\n\nSearch generated documentation quickly: `notesmd-cli search-content \"\u003Cterm>\" --vault \"\u003Cproject-name>\"` or `obsidian search query=\"\u003Cterm>\"` (fallback: `rg --glob '*.md' \"\u003Cterm>\" docs\u002F`).\n",{"name":5,"license":15,"metadata":24,"description":27,"allowed-tools":28,"compatibility":29},{"audience":25,"workflow":26},"developers","development","Explore codebases quickly using glob, grep, and targeted reads, and return compact evidence with exact file references. Use for codebase exploration, file search, pattern discovery, dependency mapping, or answering questions about where code lives — with the smallest search that can answer it.\n","read, glob, grep","opencode, copilot, antigravity","main","f7ddc0c3b3190e379bda1059d53f861bd4e1f30d","skills\u002Fdh-explore",1,"https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness","https:\u002F\u002Fgithub.com\u002Fandrescevp","2026-11-10 07:43:44",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add andrescevp\u002Fdevelopment-harness --skill dh-explore",{"tool":43,"command":44},"bunx","bunx skills add andrescevp\u002Fdevelopment-harness --skill dh-explore",{"tool":46,"command":47},"pnpm","pnpm dlx skills add andrescevp\u002Fdevelopment-harness --skill dh-explore","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-explore\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7DK6HMNFES75RNB4G6TE55T","dh-simplify","Review changed code for reuse, quality, and efficiency (three parallel reviews), then fix findings directly. Use after making changes or when asked to clean up, refactor, simplify, or improve this code.","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-simplify\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7DK6BFEQ9PVZTHKV0DR66BR","dh-setup","Audit system software, configure user MCPs\u002Fplugins, scaffold project QA (hooks + per-stack tools), bootstrap docs\u002Farchitecture with the selected architecture agent, and write harness directives into AGENTS.md. Use to check requirements or setup the environment.","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-setup\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7DK62N6CDZ2TH890AX2Z7P9","dh-semver","Apply strict Semantic Versioning — analyze commits since the last tag to determine the bump type (major\u002Fminor\u002Fpatch from conventional commit prefixes), generate an automated changelog grouped by breaking changes, features, fixes, and chores, and create a git tag locally without pushing until confirmed, handling both conventional commits and manual version decisions. Use when preparing a release, invoked by dh-execute-plan after plan completion and dh-final-review for release readiness, or when the user asks \"what version is next?\", \"bump version\", \"generate changelog\", \"tag release\", or \"what changed since last release?\".","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-semver\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7DK5SM44RAH10HM59JC6ZPZ","dh-review","Verify a plan sub-task against acceptance criteria, scope, done-when; review diff, validation, regression risk; structured verdict to tasks\u002Freview.md. Plan Alignment Mode (fast execution) is a separate mode: no sub-task selection, no diff review, no code review — it compares plan.md with plan_fast.md and writes tasks\u002Freview-fast.md (pre-execution) or tasks\u002Freview-fast-final.md (plan-end). Use after implementation, to review\u002Fverify the sub-task, or to check fast-plan alignment.","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-review\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7DK5KKZ05K0FR0ARFHA58KG","dh-resume-plan","Resume a paused phased plan from docs\u002Fplans\u002F\u003Cslug>\u002Fhandoff.md: validate the contract, detect drift, rehydrate context, mark the handoff resumed, and continue via dh-execute-plan resume mode. Use when the user says \"resume the plan\", \"continue where we stopped\", \"pick up the plan\", or \"resume after a pause\".","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-resume-plan\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7DK5E10T47JWQAJSAXJHHGD","dh-preflight","Run tests, linters, static analysis as a release gate: auto-detect tooling, check dirty state, pass\u002Ffail verdict with actionable failures (no auto-fixes). Use to run preflight, pre-release check, or validate before release.","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-preflight\u002FSKILL.md",[],[]]