Skip to content

radarist/structured-analytic-skills / skills/_TEMPLATE

skill-name-here

Verified

Third person, one or two sentences: what the skill does, then when to reach for it, with two to four quoted trigger phrases a user would actually type — "score this on TRL", "is this claim safe to ship?". Route the near misses explicitly: not for {adjacent situation} (use `sibling-skill`). No workflow summary, no angle brackets, 700 characters maximum.

FileKindSize
SKILL.mdskill md5.1 KB
evals/evals.jsonconfig1.4 KB

evals/evals.json

View on GitHub
{
  "skill_name": "skill-name-here",
  "evals": [
    {
      "id": 1,
      "case_id": "template-pos-1",
      "kind": "positive",
      "prompt": "A request phrased the way a user would phrase it, naming the situation rather than the method — the skill has to be retrieved from the description alone. Ship at least three of these.",
      "expected_output": "A response that satisfies these checks: Follows the published step order; Fills every mandatory field of the output template; States the confidence and what would change it.",
      "files": [],
      "expectations": [
        "Follows the published step order",
        "Fills every mandatory field of the output template",
        "States the confidence and what would change it"
      ],
      "skills": [
        "skill-name-here"
      ]
    },
    {
      "id": 2,
      "case_id": "template-neg-1",
      "kind": "negative",
      "prompt": "A near miss: a request that looks like this skill's territory but belongs to the sibling named in the Do NOT invoke list. Ship at least one.",
      "expected_output": "A response that satisfies these checks: Routes the request to the sibling skill; Does not apply this skill's procedure.",
      "files": [],
      "expectations": [
        "Routes the request to the sibling skill",
        "Does not apply this skill's procedure"
      ],
      "skills": [
        "sibling-skill-one"
      ]
    }
  ]
}
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall