Skip to content

cskwork/supergoal-skill / skills/supergoal

supergoal

Unverified

Route objective-driven development, verification, planning, "teach/explain", codebase learning, and skill evaluation through the Supergoal workflow. Use when Supergoal is requested or an autonomous delivery workflow is needed.

FileKindSize
SKILL.mdskill md12.8 KB
agents/analyst.mdmarkdown1.5 KB
agents/architect.mdmarkdown1.7 KB
agents/code-reviewer.mdmarkdown2.5 KB
agents/db-reader.mdmarkdown2.0 KB
agents/debugger.mdmarkdown2.0 KB
agents/designer.mdmarkdown6.3 KB
agents/executor.mdmarkdown2.8 KB
agents/explore.mdmarkdown2.0 KB
agents/qa-auditor.mdmarkdown4.3 KB
agents/qa-tester.mdmarkdown3.2 KB
agents/security-reviewer.mdmarkdown1.2 KB
agents/skill-forger.mdmarkdown1.6 KB
agents/skill-miner.mdmarkdown1.6 KB
reference/agent-browser.mdmarkdown2.8 KB
reference/arch.mdmarkdown5.1 KB
reference/archify.mdmarkdown3.6 KB
reference/db-access.mdmarkdown2.9 KB
reference/debugging.mdmarkdown6.5 KB
reference/delivery-gate.mdmarkdown6.6 KB
reference/domain-context.mdmarkdown7.8 KB
reference/domain-rules.mdmarkdown1.6 KB
reference/engagement.mdmarkdown3.8 KB
reference/functional-ui.mdmarkdown6.4 KB
reference/harness-eval.mdmarkdown28.7 KB
reference/interview.mdmarkdown7.7 KB
reference/learn-domain.mdmarkdown12.7 KB
reference/market-research.mdmarkdown1.7 KB
reference/observability.mdmarkdown5.0 KB
reference/plan-grounding.mdmarkdown4.3 KB
reference/playwright-cli.mdmarkdown2.6 KB
reference/prototype.mdmarkdown4.5 KB
reference/qa-only.mdmarkdown12.7 KB
reference/qa.mdmarkdown7.9 KB
reference/reporting.mdmarkdown1.5 KB
reference/research.mdmarkdown2.7 KB
reference/review-only.mdmarkdown2.4 KB
reference/role-loop.mdmarkdown26.7 KB
reference/rules.mdmarkdown982 B
reference/skill-mine.mdmarkdown7.6 KB
reference/taste-aesthetics.mdmarkdown7.5 KB
reference/taste-skill-v2.mdmarkdown18.8 KB
reference/taste-sources.mdmarkdown3.0 KB
reference/teach.mdmarkdown28.0 KB
reference/ui-ux.mdmarkdown4.0 KB
reference/vercel-host.mdmarkdown3.6 KB
reference/wayfinder.mdmarkdown7.2 KB
templates/GOAL.mdmarkdown1.3 KB
templates/PLAN.mdmarkdown1.4 KB
templates/QA.mdmarkdown1.2 KB
templates/R-LOOP.mdmarkdown569 B
templates/Z-DONE.mdmarkdown301 B
templates/arch-report.htmlother8.1 KB
templates/commit-gate.shexecutablescript11.6 KB
templates/contrast-gate.mjsexecutablescript4.3 KB
templates/db-access/.env.exampleother451 B
templates/db-access/check-connection.shexecutablescript134 B
templates/db-access/db-access.cmdscript39 B
templates/db-access/db-access.mjsexecutablescript5.2 KB
templates/db-access/read-only-query.shexecutablescript138 B
templates/db-access/schema-summary.shexecutablescript132 B
templates/domain-agent/code-map.mdmarkdown744 B
templates/domain-agent/config.jsonconfig291 B
templates/domain-agent/decisions/README.mdmarkdown270 B
templates/domain-agent/flows/README.mdmarkdown800 B
templates/domain-agent/freshness.mdmarkdown1.2 KB
templates/domain-agent/glossary.mdmarkdown781 B
templates/domain-agent/index.mdmarkdown1.3 KB
templates/domain-agent/invariants.mdmarkdown504 B
templates/domain-agent/qa/README.mdmarkdown879 B
templates/domain-agent/qa/nav-map.mdmarkdown1.2 KB
templates/domain-agent/test-map.mdmarkdown432 B
templates/domain-agent/tickets/README.mdmarkdown204 B
templates/domain-onboarding.htmlother9.2 KB
templates/harness-eval-case.yamlconfig4.4 KB
templates/harness-eval-cases/authored/authored-underspec-001-deepmerge.yamlconfig2.2 KB
templates/harness-eval-cases/authored/authored-underspec-002-csvline.yamlconfig2.0 KB
templates/harness-eval-cases/authored/authored-underspec-003-authz-cache.yamlconfig1.6 KB
templates/harness-eval-cases/fixtures/README.mdmarkdown2.8 KB
templates/harness-eval-cases/fixtures/revfactory-case-002-async-race/package.jsonmanifest124 B
templates/harness-eval-cases/fixtures/revfactory-case-002-async-race/src/cache.mjsscript494 B
templates/harness-eval-cases/fixtures/revfactory-case-002-async-race/test/cache.hidden.test.mjsscript2.2 KB
templates/harness-eval-cases/fixtures/revfactory-case-002-async-race/test/cache.visible.test.mjsscript950 B
templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/package.jsonmanifest125 B
templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/src/order.mjsscript1.3 KB
templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/test/order.hidden.test.mjsscript2.2 KB
templates/harness-eval-cases/fixtures/revfactory-case-003-refactoring/test/order.visible.test.mjsscript1.2 KB
templates/harness-eval-cases/fixtures/underspec-001-deepmerge/package.jsonmanifest124 B
templates/harness-eval-cases/fixtures/underspec-001-deepmerge/src/merge.mjsscript84 B
templates/harness-eval-cases/fixtures/underspec-001-deepmerge/test/merge.hidden.test.mjsscript1013 B
templates/harness-eval-cases/fixtures/underspec-001-deepmerge/test/merge.visible.test.mjsscript276 B
templates/harness-eval-cases/fixtures/underspec-002-csvline/package.jsonmanifest122 B
templates/harness-eval-cases/fixtures/underspec-002-csvline/src/csv.mjsscript77 B
templates/harness-eval-cases/fixtures/underspec-002-csvline/test/csv.hidden.test.mjsscript804 B
templates/harness-eval-cases/fixtures/underspec-002-csvline/test/csv.visible.test.mjsscript240 B
templates/harness-eval-cases/fixtures/underspec-003-authz-cache/package.jsonmanifest126 B
templates/harness-eval-cases/fixtures/underspec-003-authz-cache/src/authorizer.mjsscript601 B
templates/harness-eval-cases/fixtures/underspec-003-authz-cache/test/authorizer.hidden.test.mjsscript3.8 KB
templates/harness-eval-cases/fixtures/underspec-003-authz-cache/test/authorizer.visible.test.mjsscript1.2 KB
templates/harness-eval-cases/revfactory-case-001-rest-api.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-002-bug-fix.yamlconfig2.4 KB
templates/harness-eval-cases/revfactory-case-003-refactoring.yamlconfig2.4 KB
templates/harness-eval-cases/revfactory-case-004-documentation.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-005-complex.yamlconfig2.0 KB
templates/harness-eval-cases/revfactory-case-006-research.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-007-interpreter.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-008-microservice.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-009-sql-engine.yamlconfig2.0 KB
templates/harness-eval-cases/revfactory-case-010-crdt.yamlconfig2.0 KB
templates/harness-eval-cases/revfactory-case-011-raft-kv.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-012-spreadsheet.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-013-bytecode-vm.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-014-event-sourcing.yamlconfig2.1 KB
templates/harness-eval-cases/revfactory-case-015-lsp.yamlconfig2.3 KB
templates/harness-eval-cases/run-local-eval.mjsscript43.3 KB
templates/harness-eval-cases/run-underspec-n3.mjsscript41.1 KB
templates/harness-eval-external/deepswe/README.mdmarkdown9.9 KB
templates/harness-eval-external/deepswe/prepare-supergoal-arm.mjsscript4.4 KB
templates/harness-eval-external/deepswe/run-default-suite.mjsscript6.1 KB
templates/harness-eval-external/deepswe/run-full-cycle.mjsscript25.3 KB
templates/harness-eval-external/deepswe/task-set.yamlconfig12.2 KB
templates/harness-eval-external/featadd/README.mdmarkdown3.9 KB
templates/harness-eval-external/featadd/features.tsvother1.6 KB
templates/harness-eval-external/featadd/gen.shscript4.0 KB
templates/harness-eval-external/featadd/package.pyscript6.2 KB
templates/harness-eval-gate.mjsscript24.9 KB
templates/harness-eval-report.mdmarkdown5.8 KB
templates/harness-eval-result.jsonconfig11.9 KB
templates/harness-eval-runner.mjsscript19.9 KB
templates/harness-eval-stats.mjsscript1.8 KB
templates/learn-grounding-gate.mjsscript6.1 KB
templates/observability/heartbeat.schema.jsonconfig2.5 KB
templates/observability/sg-emit.shexecutablescript5.4 KB
templates/qa-gate.shexecutablescript6.9 KB
templates/qa-only-gate.shexecutablescript5.1 KB
templates/qa-report.mdmarkdown2.8 KB
templates/rules.mdmarkdown301 B
templates/run-state-gate.mjsscript2.2 KB
templates/run-state.jsonconfig474 B
templates/skill-frontmatter-gate.mjsscript3.7 KB
templates/skill-install-audit.mjsexecutablescript3.7 KB
templates/skill-mine/mine.mjsscript7.8 KB
templates/skill.md.templateother568 B
templates/teach-lesson-gate.mjsscript5.4 KB
templates/teach/README.mdmarkdown4.1 KB
templates/teach/assets/lesson-book.jsscript5.8 KB
templates/teach/assets/lesson-template.htmlother6.1 KB
templates/teach/assets/lesson.cssother11.8 KB
templates/teach/assets/quiz.jsscript3.2 KB

reference/skill-mine.md

View on GitHub
# SKILL-MINE mode - mine history, suggest 3-5 skills, forge the picked one

Use when the user wants to turn repeated work into a reusable skill: "make a skill", "스킬 만들어",
"learn new skill", "make skill from history/conversation", "이거 자주 하는데 스킬로/자동화". It mines
recent agent session history, surfaces 3-5 candidate skills ranked by frequency x payoff, lets the user
pick (or reject, or name a new one), then forges ONE cross-agent-portable SKILL.md and installs it.

Writes NO production code and needs NO worktree. Read-only except the generated skill directory, its
install targets, and the journal. The human pick is a hard gate: never create or install a skill the
user did not approve - this is the validation gate that Hermes-style autonomous skill creation lacks.

## Pipeline

`Intake -> Window -> Mine -> Rank -> Suggest -> [Human pick/reject] -> Forge -> Verify -> Install -> Journal`

| Phase | Goal | Writes | Exit gate |
|---|---|---|---|
| Intake | Capture target agent(s), repo scope, what "useful" means | run note | scope + install targets named |
| Window | Pick adaptive 7-30d window | run note | window days + rationale recorded |
| Mine | Run the mechanical miner | - | miner JSON obtained |
| Rank | Cluster intents, score by frequency x payoff, drop already-skilled | run note | <=5 ranked candidates |
| Suggest | Show 3-5 + evidence; offer "new" and "reject all" | - | candidates shown with recurrence/example |
| Human pick | User picks / rejects / names new | run note | explicit approval recorded (or stop) |
| Forge | Generate portable SKILL.md | skill dir | frontmatter + body within limits |
| Verify | Gate + adversarial check | - | gate exits 0; trigger matches mined pattern |
| Install | Copy/symlink to each chosen agent dir | skill dirs | present in every target; none clobbered |
| Journal | Record mining evidence + decision | `teach/` | journal entry written |

## Window (adaptive)

The miner picks the window: start 7d; if <3 sessions in window, widen to 14 then 30. An active repo
satisfies 7d. Sparse history widens AND lowers `minsup` so thin signal still surfaces.

`node templates/skill-mine/mine.mjs [--repo <slug>] [--all] [--minsup 0.2] [--days N]`

Default repo = current cwd (Claude Code slug = cwd with `/` and `.` replaced by `-`). `--all` mines every
repo. The miner reads `~/.claude/projects/<slug>/*.jsonl` (full tool-call transcripts), NOT the
prompt-only `~/.claude/history.jsonl`.

## Mine + Rank

The miner does the cheap mechanical part; the agent does the semantic part. Dispatch `skill-miner`.

- **Use, do not trust, tool n-grams.** Raw tool-name n-grams (`Bash > Bash`) are generic; context only,
  never a candidate by themselves.
- **Bash signatures** (verb+subcommand, noise-filtered) reveal concrete repeated procedures - e.g.
  `git add`+`git commit`+`git tag`+`gh release` = a release procedure.
- **Intent hints** (first user prompt per session) are the strongest signal. Cluster by intent (one
  actor + one repeated goal each); corroborate with bash signatures. Each recurring cluster is a candidate.
- **Score** = support (fraction of sessions) x payoff (steps/toil removed). Rank, keep top 3-5.
- **Drop already-skilled**: exclude anything in the miner's `alreadySkilled` unless the user asks to
  improve one.

## Suggest + Human pick (anti over-suggestion gate)

Surface a candidate ONLY when `support >= minsup AND it plausibly recurs` (Horvitz mixed-initiative: act
only when expected value beats inaction). Present 3-5 max via `AskUserQuestion`, each with: name, one-line
what+when, recurrence (N sessions / example), estimated payoff. Always include a "make a different skill
(describe it)" option and a "none of these" option. Rejection is free and ends the run cleanly; never
re-pitch a rejected candidate.

## Forge (cross-agent-portable SKILL.md)

A skill is a DIRECTORY with `SKILL.md` as the entrypoint (agentskills.io open standard). Dispatch
`skill-forger`; generate from `templates/skill.md.template`. Portable rules:

- **Directory name = command name**: lowercase letters/digits/hyphens, <=64 chars, no reserved word
  (`anthropic`, `claude`). Frontmatter `name` matches the directory.
- **description** states what AND when, key use case first. Keep `description` + `when_to_use` combined
  <=1536 chars (the skill-listing truncation cap). Description quality IS the discovery mechanism.
- **Body <=~5k tokens** (Claude Code keeps only the first 5k after compaction). Push long reference,
  data, or scripts to bundled files loaded on demand (progressive disclosure), not the body.
- **Stay portable**: the core SKILL.md must run on any agentskills.io agent. Do not depend on Claude
  Code-only frontmatter (`allowed-tools`, `context: fork`, `disable-model-invocation`); add those only as
  an optional Claude-tuned variant if the user asks.

## Verify

1. `node templates/skill-frontmatter-gate.mjs <skill-dir>` exits 0 only when name/description/body pass
   the portable limits above. Never edit the gate to pass.
2. Adversarial check: the description's "when" must match the mined trigger, and the body's steps must
   reproduce the mined procedure. If the skill wraps a command, dry-run it once.

## Install (collect in `~/.agents/skills/`, then symlink to each chosen agent)

Skills are COLLECTED in one canonical store - `~/.agents/skills/<name>/`, a plain real dir (NOT a symlink
into a skill-manager store). This is the standard, default location: always forge the real `SKILL.md` dir
HERE first. Custom skills do NOT auto-sync across agents/surfaces, so symlink that one canonical dir into
each agent target picked at Intake - one edit then lands everywhere:

| Agent | Personal install (symlink -> canonical) | Project dir |
|---|---|---|
| Claude Code | `~/.claude/skills/<name>` -> `../../.agents/skills/<name>` (relative) | `.claude/skills/<name>` -> canonical |
| Codex | `~/.codex/skills/<name>` -> `../../.agents/skills/<name>` (relative) | personal unless a project dir is confirmed |
| opencode | `~/.config/opencode/skills/<name>` -> canonical (absolute) | personal unless confirmed |
| Hermes | `~/.hermes/skills/<name>` -> canonical (absolute) | - |

`sync-skill` does the propagation from the canonical dir. Only when a standalone (no-symlink) setup is
explicitly required, fall back to copying the real dir into each agent. Never silently overwrite an
existing skill of the same name; on collision show a diff and ask.

## Journal

Append to `teach/skill-mined-<name>-YYYY-MM-DD.md`: the mining window, the candidate set shown, what the
user picked/rejected, the recurrence evidence, and the install targets. Create `teach/` if missing.

## Always state the source location (required)

End every SKILL-MINE run by telling the user where the canonical SOURCE skill(s) live - the single dir to
edit, which the per-agent installs point at. Put it on the last line of your reply, e.g.:

`Source: ~/.agents/skills/<name>/  (edit here; agents symlink to it)`

Use the actual canonical path chosen at Install (default `~/.agents/skills/<name>/`). If skills were
installed as standalone real copies per agent instead, list each copy's path. Never end without saying
where the source is.

## Stop conditions

- User rejects all / picks none: stop cleanly; record the rejection in the journal (informs next run).
- No candidate clears `minsup`: report "no repeated pattern strong enough yet", suggest a wider window or
  `--all`; do not invent a skill.
- Name collides with an existing skill: show the diff, ask before overwrite; never clobber silently.
- A chosen agent's install dir does not exist: report it; install to the agents that are present.
- A skill would embed secrets/tokens/PII surfaced from history: redact; never write them into a skill.
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