[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79NPBE4D89QDMPDFGT5X498":3,"skill-same:01M79NPBE4D89QDMPDFGT5X498":50},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M79NPBE4D89QDMPDFGT5X498","ecc-recipes",null,"Map a described workflow to the right ECC command group with run-order and stop condition, or browse all command-group recipe families read live from the commands directory. Advisory only — never executes. Use when asked which commands run a workflow, the command sequence for a task, or to list ECC pipelines; not for executing the task (route to the command itself), single-command docs (use ecc-guide), or prompt rewrites (use prompt-optimizer).","JunMystery\u002FAgent-Guidance","JunMystery","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F161468934?v=4","01M79MTMV8F0BY8NK1A92RA8A0","Jun","01M79MTMWCFBKPHN5B25E6V20B",0,"MIT","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fecc-recipes\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ecc-recipes\ndescription: Map a described workflow to the right ECC command group with run-order and stop condition, or browse all command-group recipe families read live from the commands directory. Advisory only — never executes. Use when asked which commands run a workflow, the command sequence for a task, or to list ECC pipelines; not for executing the task (route to the command itself), single-command docs (use ecc-guide), or prompt rewrites (use prompt-optimizer).\nargument-hint: \u003Cworkflow description | empty=list all>\norigin: community\nauthor: KyawZinLatt\nmetadata:\n  version: \"1.0.0\"\n---\n\n# ECC Recipes\n\nOne entry point for \"which group of ECC slash-commands runs my workflow, in what\norder, and when do I stop.\" Also browses every command-group recipe family.\n\nFills the gap between two existing skills:\n\n- `ecc-guide` — lists commands and where to read docs, but as a flat catalog.\n- `prompt-optimizer` — matches a task to components, but outputs a single prompt,\n  not a multi-command group with run-order and stop condition.\n\nThis skill adds: **family grouping + run-order + stop condition.**\n\n## When to Activate\n\n- \"Which command group do I run for \u003Cworkflow>?\"\n- \"What's the command sequence to build an MVP \u002F fix a defect \u002F refactor?\"\n- \"Show me all ECC command-group recipes\" (catalog mode)\n- \"How many workflow pipelines does ECC have?\"\n- User invokes `\u002Fecc-recipes` with or without a description.\n\n### Do Not Use When\n\n- User wants the task done now — route to the actual command, don't describe it.\n- User wants deep docs for ONE command — use `ecc-guide`.\n- User wants a draft prompt rewritten — use `prompt-optimizer`.\n\n## Core Principle\n\n**Answer from current files, not memory.** The command set changes; never\nhardcode counts or member lists. Read the live `commands\u002F` directory each run,\nthen classify into families.\n\n### Live reads\n\nResolve the commands directory (first that exists), then list names:\n\n```bash\nfor D in \\\n  \"$HOME\"\u002F.claude\u002Fplugins\u002Fmarketplaces\u002Fecc\u002Fcommands \\\n  \"$HOME\"\u002F.claude\u002Fplugins\u002Fcache\u002Fecc\u002Fecc\u002F*\u002Fcommands \\\n  .\u002Fcommands \\\n  .\u002F.claude\u002Fcommands \\\n  \"$HOME\"\u002F.claude\u002Fcommands; do\n  [ -d \"$D\" ] && CMD_DIR=\"$D\" && break\ndone\n[ -z \"${CMD_DIR:-}\" ] && { echo \"No ECC commands directory found.\"; return 1; }\nfind \"$CMD_DIR\" -maxdepth 1 -name '*.md' -exec basename {} .md \\; | sort\n```\n\nOptionally read `manifests\u002Finstall-*.json` if present for richer grouping. Use\nthe smallest set of reads needed.\n\n## Family Classification (by prefix)\n\nGroup command names by leading prefix; map known singletons by hand. Families are\nderived live — the table below is the *classification rule*, not a frozen list.\n\n| Family prefix | Recipe meaning | Typical run-order |\n|---|---|---|\n| `orch-*` | gated Research, Plan, TDD, Review, Commit per task type | pick one orch-* by task kind; it runs its own internal phases |\n| `multi-*` | multi-model workflow | `multi-plan` then `multi-execute` then review (or `multi-workflow` end-to-end) |\n| `prp-*` | PRD to plan to implement to PR pipeline | `prp-prd` then `prp-plan` then `prp-implement` then `prp-commit` then `prp-pr` |\n| `epic-*` | large multi-unit epic, parallel | `epic-decompose` then `epic-claim` then `epic-validate` then `epic-review` then `epic-unblock` then `epic-sync` then `epic-publish` |\n| `loop-*` | managed autonomous loop and monitor | `loop-start \u003Cpattern>` then watch with `loop-status` |\n| `gan-*` | generator and evaluator loop | `gan-build` (code) or `gan-design` (UI); self-looping |\n| `*-build` \u002F `*-review` \u002F `*-test` | per-language CI triad | `\u003Clang>-test` (TDD) then `\u003Clang>-build` (fix) then `\u003Clang>-review` |\n| `hookify-*` | behavior-hook management | `hookify` then `hookify-list` then `hookify-configure` |\n| `learn` \u002F `instinct-*` \u002F `evolve` \u002F `promote` \u002F `prune` | continuous-learning | `learn` then `instinct-status` then `evolve` then `promote` |\n| singletons | `santa-loop`, `plan`, `plan-prd`, `pr`, `code-review`, `checkpoint`, etc. | standalone or glue between groups |\n\nAny command not matching a prefix rule → list it under **singletons** with its\none-line description.\n\n## How It Works\n\n```\n1. Live-read command names from CMD_DIR.\n2. Classify into families by prefix and a singleton map.\n3. If a workflow description was given -> MATCH MODE.\n   If none -> CATALOG MODE.\n4. Advisory only: print the plan. Never run the matched commands.\n```\n\n### Catalog mode (no description)\n\nOutput the family table: each family, member count, members, one-line meaning,\ntypical run-order. End with the total command count and a prompt to describe a\nworkflow for a matched recipe.\n\n### Match mode (description given)\n\n1. Restate the workflow in one sentence.\n2. Pick the best 1-2 families; say WHY in one line each.\n3. **Run-order block** — exact command sequence for the matched family.\n4. **Stop condition** — always explicit (max-runs, completion-signal,\n   review-passes, or single-shot). For autonomous loops, warn about subscription\n   burn and recommend a backstop bound.\n5. **Where to read** — the `commands\u002F\u003Cname>.md` path plus `\u002Fecc-guide \u003Cname>`.\n\n## Output Template (match mode)\n\n```\nWorkflow: \u003Cone-sentence restatement>\n\nBest fit: \u003Cfamily> — \u003Cwhy>\n(Alt: \u003Cfamily> — \u003Cwhy>)\n\nRun-order:\n  \u002F\u003Ccmd1>   # job\n  \u002F\u003Ccmd2>   # job\n  \u002F\u003Ccmd3>   # job\n  STOP when: \u003Ccondition>\n  WARNING (autonomous loops only): an unbounded loop burns subscription\u002Fcredits —\n  add a max-iteration or max-cost backstop alongside the completion signal.\n\nRead full docs:\n  commands\u002F\u003Ccmd1>.md   (or: \u002Fecc-guide \u003Ccmd1>)\n```\n\n## Examples\n\n**Catalog:** `\u002Fecc-recipes` → prints the family table and total count.\n\n**Match:** `\u002Fecc-recipes plan a whole app upfront then auto-build with adversarial\nreview until done` → Best fit: `loop-*` (autonomous) wrapping `gan-*` or\n`santa-loop` (adversarial). Run-order: `plan-prd` then\n`loop-start rfc-dag --mode safe` then monitor `loop-status`; STOP when all units\npass review N consecutive times (add a max-iteration backstop to bound burn).\n\n**Match:** `\u002Fecc-recipes fix a bug in my Go service` → Best fit: `orch-fix-defect`\n(reproduce, fix, review, commit). Alt: `go-test` then `go-build` then\n`go-review`. STOP: regression test green and review pass.\n\n## Non-Goals\n\n- Not an executor — advisory only.\n- Not per-command deep docs — that's `ecc-guide`.\n- Not prompt rewriting — that's `prompt-optimizer`.\n- Never hardcode command counts or member lists — always live-read.\n","# ECC Recipes\n\nOne entry point for \"which group of ECC slash-commands runs my workflow, in what\norder, and when do I stop.\" Also browses every command-group recipe family.\n\nFills the gap between two existing skills:\n\n- `ecc-guide` — lists commands and where to read docs, but as a flat catalog.\n- `prompt-optimizer` — matches a task to components, but outputs a single prompt,\n  not a multi-command group with run-order and stop condition.\n\nThis skill adds: **family grouping + run-order + stop condition.**\n\n## When to Activate\n\n- \"Which command group do I run for \u003Cworkflow>?\"\n- \"What's the command sequence to build an MVP \u002F fix a defect \u002F refactor?\"\n- \"Show me all ECC command-group recipes\" (catalog mode)\n- \"How many workflow pipelines does ECC have?\"\n- User invokes `\u002Fecc-recipes` with or without a description.\n\n### Do Not Use When\n\n- User wants the task done now — route to the actual command, don't describe it.\n- User wants deep docs for ONE command — use `ecc-guide`.\n- User wants a draft prompt rewritten — use `prompt-optimizer`.\n\n## Core Principle\n\n**Answer from current files, not memory.** The command set changes; never\nhardcode counts or member lists. Read the live `commands\u002F` directory each run,\nthen classify into families.\n\n### Live reads\n\nResolve the commands directory (first that exists), then list names:\n\n```bash\nfor D in \\\n  \"$HOME\"\u002F.claude\u002Fplugins\u002Fmarketplaces\u002Fecc\u002Fcommands \\\n  \"$HOME\"\u002F.claude\u002Fplugins\u002Fcache\u002Fecc\u002Fecc\u002F*\u002Fcommands \\\n  .\u002Fcommands \\\n  .\u002F.claude\u002Fcommands \\\n  \"$HOME\"\u002F.claude\u002Fcommands; do\n  [ -d \"$D\" ] && CMD_DIR=\"$D\" && break\ndone\n[ -z \"${CMD_DIR:-}\" ] && { echo \"No ECC commands directory found.\"; return 1; }\nfind \"$CMD_DIR\" -maxdepth 1 -name '*.md' -exec basename {} .md \\; | sort\n```\n\nOptionally read `manifests\u002Finstall-*.json` if present for richer grouping. Use\nthe smallest set of reads needed.\n\n## Family Classification (by prefix)\n\nGroup command names by leading prefix; map known singletons by hand. Families are\nderived live — the table below is the *classification rule*, not a frozen list.\n\n| Family prefix | Recipe meaning | Typical run-order |\n|---|---|---|\n| `orch-*` | gated Research, Plan, TDD, Review, Commit per task type | pick one orch-* by task kind; it runs its own internal phases |\n| `multi-*` | multi-model workflow | `multi-plan` then `multi-execute` then review (or `multi-workflow` end-to-end) |\n| `prp-*` | PRD to plan to implement to PR pipeline | `prp-prd` then `prp-plan` then `prp-implement` then `prp-commit` then `prp-pr` |\n| `epic-*` | large multi-unit epic, parallel | `epic-decompose` then `epic-claim` then `epic-validate` then `epic-review` then `epic-unblock` then `epic-sync` then `epic-publish` |\n| `loop-*` | managed autonomous loop and monitor | `loop-start \u003Cpattern>` then watch with `loop-status` |\n| `gan-*` | generator and evaluator loop | `gan-build` (code) or `gan-design` (UI); self-looping |\n| `*-build` \u002F `*-review` \u002F `*-test` | per-language CI triad | `\u003Clang>-test` (TDD) then `\u003Clang>-build` (fix) then `\u003Clang>-review` |\n| `hookify-*` | behavior-hook management | `hookify` then `hookify-list` then `hookify-configure` |\n| `learn` \u002F `instinct-*` \u002F `evolve` \u002F `promote` \u002F `prune` | continuous-learning | `learn` then `instinct-status` then `evolve` then `promote` |\n| singletons | `santa-loop`, `plan`, `plan-prd`, `pr`, `code-review`, `checkpoint`, etc. | standalone or glue between groups |\n\nAny command not matching a prefix rule → list it under **singletons** with its\none-line description.\n\n## How It Works\n\n```\n1. Live-read command names from CMD_DIR.\n2. Classify into families by prefix and a singleton map.\n3. If a workflow description was given -> MATCH MODE.\n   If none -> CATALOG MODE.\n4. Advisory only: print the plan. Never run the matched commands.\n```\n\n### Catalog mode (no description)\n\nOutput the family table: each family, member count, members, one-line meaning,\ntypical run-order. End with the total command count and a prompt to describe a\nworkflow for a matched recipe.\n\n### Match mode (description given)\n\n1. Restate the workflow in one sentence.\n2. Pick the best 1-2 families; say WHY in one line each.\n3. **Run-order block** — exact command sequence for the matched family.\n4. **Stop condition** — always explicit (max-runs, completion-signal,\n   review-passes, or single-shot). For autonomous loops, warn about subscription\n   burn and recommend a backstop bound.\n5. **Where to read** — the `commands\u002F\u003Cname>.md` path plus `\u002Fecc-guide \u003Cname>`.\n\n## Output Template (match mode)\n\n```\nWorkflow: \u003Cone-sentence restatement>\n\nBest fit: \u003Cfamily> — \u003Cwhy>\n(Alt: \u003Cfamily> — \u003Cwhy>)\n\nRun-order:\n  \u002F\u003Ccmd1>   # job\n  \u002F\u003Ccmd2>   # job\n  \u002F\u003Ccmd3>   # job\n  STOP when: \u003Ccondition>\n  WARNING (autonomous loops only): an unbounded loop burns subscription\u002Fcredits —\n  add a max-iteration or max-cost backstop alongside the completion signal.\n\nRead full docs:\n  commands\u002F\u003Ccmd1>.md   (or: \u002Fecc-guide \u003Ccmd1>)\n```\n\n## Examples\n\n**Catalog:** `\u002Fecc-recipes` → prints the family table and total count.\n\n**Match:** `\u002Fecc-recipes plan a whole app upfront then auto-build with adversarial\nreview until done` → Best fit: `loop-*` (autonomous) wrapping `gan-*` or\n`santa-loop` (adversarial). Run-order: `plan-prd` then\n`loop-start rfc-dag --mode safe` then monitor `loop-status`; STOP when all units\npass review N consecutive times (add a max-iteration backstop to bound burn).\n\n**Match:** `\u002Fecc-recipes fix a bug in my Go service` → Best fit: `orch-fix-defect`\n(reproduce, fix, review, commit). Alt: `go-test` then `go-build` then\n`go-review`. STOP: regression test green and review pass.\n\n## Non-Goals\n\n- Not an executor — advisory only.\n- Not per-command deep docs — that's `ecc-guide`.\n- Not prompt rewriting — that's `prompt-optimizer`.\n- Never hardcode command counts or member lists — always live-read.\n",{"name":5,"author":24,"origin":25,"metadata":26,"description":7,"argument-hint":28},"KyawZinLatt","community",{"version":27},"1.0.0","\u003Cworkflow description | empty=list all>","main","5d0a87185c0e172c3901e2a6e5916b6d544b8b94","skills\u002Fecc-recipes","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance","https:\u002F\u002Fgithub.com\u002FJunMystery","AI is the typist, I am the architect. Building efficient, secure, and user-centric products through disciplined AI prompt engineering.","2026-11-13 17:41:25",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add JunMystery\u002FAgent-Guidance --skill ecc-recipes",{"tool":42,"command":43},"bunx","bunx skills add JunMystery\u002FAgent-Guidance --skill ecc-recipes",{"tool":45,"command":46},"pnpm","pnpm dlx skills add JunMystery\u002FAgent-Guidance --skill ecc-recipes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fecc-recipes\u002FSKILL.md",true,[],[51,57,63,69,75,81],{"skillNo":52,"name":53,"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":54,"categories":55,"keywords":56,"publishedAt":19},"01M79QR1E309VJ6CTQKB32AWWA","zero-trust-architecture-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fzero-trust-architecture-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"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":60,"categories":61,"keywords":62,"publishedAt":19},"01M79QQV7GHYR02DYGN41S23WN","xss-filter-evasion-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxss-filter-evasion-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"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":66,"categories":67,"keywords":68,"publishedAt":19},"01M79QQNSN7YB8XB61FFSCS3WH","xs-leaks-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxs-leaks-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"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":72,"categories":73,"keywords":74,"publishedAt":19},"01M79QQHZZJKFDY9132G5A65C2","xpath-injection-prevention-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxpath-injection-prevention-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"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":78,"categories":79,"keywords":80,"publishedAt":19},"01M79QQB9ZSD3DJG8658EHQXR1","xml-security-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxml-security-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"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":84,"categories":85,"keywords":86,"publishedAt":19},"01M79QQ60WKV7PFMXWT9CW8PM6","xml-external-entity-prevention-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxml-external-entity-prevention-cheat-sheet\u002FSKILL.md",[],[]]