JPeetz/agent-skills / skills/skill-development/skill-lifecycle-foundry
skill-lifecycle-foundry
VerifiedUse this skill when mining, authoring, personalizing, or generalizing agent skills.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 595 B |
| LICENSE | other | 1.1 KB |
| SKILL.md | skill md | 7.6 KB |
| evals/evals.json | config | 4.0 KB |
| references/release-checklist.md | markdown | 1.2 KB |
| references/sources.md | markdown | 464 B |
| scripts/scan_sessions.py | script | 2.6 KB |
evals/evals.json
View on GitHub{
"skill": "skill-lifecycle-foundry",
"version": "1.0.0",
"cases": [
{
"id": "e1",
"description": "Should trigger: mine session history for skills",
"input": "Mine my session history and archives for repeated workflows that should become skills.",
"shouldTrigger": true,
"expect": "Produce a candidate list with repeat evidence and dispositions",
"assertions": [
"Scans at least one source of session/archive history",
"Returns a shortlist of candidate workflows with repeat evidence",
"Assigns each candidate a disposition (personal/publishable/skip)"
]
},
{
"id": "e2",
"description": "Should trigger: draft a new skill",
"input": "Turn our recurring triage workflow into a new SKILL.md file.",
"shouldTrigger": true,
"expect": "Create a folder + SKILL.md with frontmatter and canonical sections",
"assertions": [
"Folder slug is lowercase-kebab",
"Frontmatter name matches the folder",
"Body includes When to Use, Prerequisites, Procedure, Pitfalls, Verification"
]
},
{
"id": "e3",
"description": "Should trigger: personalize an existing skill",
"input": "This downloaded skill doesn't trigger when I say things naturally. Personalize it for me.",
"shouldTrigger": true,
"expect": "Rewrite phrasing/examples to local tools and user language",
"assertions": [
"Rewrites at least one example to local phrasing",
"Keeps secrets and machine-local paths out",
"Explains what changed and why"
]
},
{
"id": "e4",
"description": "Should trigger: generalize for public release",
"input": "Generalize this private skill so I can publish it to GitHub.",
"shouldTrigger": true,
"expect": "Redact secrets/paths and make examples portable",
"assertions": [
"Sweeps and redacts keys, hostnames, and internal facts",
"Replaces machine-specific paths with relative or ~-based ones",
"Confirms a secret scan of the released file returns nothing"
]
},
{
"id": "e5",
"description": "Should trigger: run release checklist before publishing",
"input": "Run the release checklist before this skill ships public.",
"shouldTrigger": true,
"expect": "Walk references/release-checklist.md and report each line satisfied",
"assertions": [
"Checks LICENSE, CHANGELOG, evals, references exist",
"Confirms description <=60 chars and ends in a period",
"Reports all checklist items satisfied before publication"
]
},
{
"id": "e6",
"description": "Should trigger: audit trigger fit",
"input": "Audit this skill and tell me why it undertriggers.",
"shouldTrigger": true,
"expect": "Diagnose trigger/description issues and propose fixes",
"assertions": [
"Reviews the description for trigger wording",
"Lists undertrigger/overtrigger friction with P0/P1/P2 severity",
"Proposes a concrete description/path change"
]
},
{
"id": "n1",
"description": "Not trigger: one-off task question",
"input": "Write a shell snippet to rename files.",
"shouldTrigger": false,
"expect": "Recognize a one-off snippet request, not a skill-lifecycle task",
"assertions": [
"Does not enter the mining/drafting procedure for a whole skill",
"Frames the response as a snippet, not a SKILL.md authoring"
]
},
{
"id": "n2",
"description": "Not trigger: is simply building one skill directly",
"input": "Build me the model-routing skill from scratch now.",
"shouldTrigger": false,
"expect": "Recognize this is a concrete skill build, not lifecycle governance",
"assertions": [
"Delegates to the concrete skill authoring path",
"Does not invoke the whole lifecycle/mine loop unless asked to generalize from real data"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |