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/debugging.md

View on GitHub
# Debugging - DEBUG mode

DEBUG is deep-and-narrow. Use one driving `debugger` (`agents/debugger.md`); spawn helpers only for independent probes
and save summaries in the vault.

Reproduce exit gate: deterministic repro, cheap to re-run after every probe. No trusted loop, no fix. If
none can be built, STOP and report. For web/UI bugs, drive through `qa-tester` and `reference/qa.md`.

## Read-only until the cause is confirmed

Through Reproduce and Diagnose, analyze only. First source write waits until one root cause has direct
evidence and a written fix plan.

## Observe-first triage - live evidence before code

For a RUNNING-system bug (UI/API/data/auth/perf), do NOT start with code reading or git archaeology.
History narrows WHEN; live observation narrows WHERE. Do WHERE first.

1. **Observe the failing flow at the symptom's boundary.** Reproduce it in the real environment
   and capture actual artifacts: devtools Network tab / Playwright HAR (call ORDER + payloads),
   API responses, logs, DB/queue records. Diff actual vs expected at that boundary - a missing
   field, an out-of-order dependency call, or an unexpected status often ends the search in
   minutes. For a web/UI symptom, drive this through `qa-tester` (`reference/qa.md`): load the
   repo's `.domain-agent/qa/nav-map.md` to reach the exact screen (its entry/auth flow, popups,
   new tabs), then capture the screen's real calls with `agent-browser network requests`
   (`network request <id>` for details) - the method + path + status it actually fires. That pins screen -> exact
   endpoint, so you open only the backend code that owns it instead of guessing where the symptom
   lives. If no nav-map exists yet, build one first (`reference/qa.md` "Navigation map"); if a saved
   entry no longer matches the live site (selector miss, route 404, popup target moved, API path
   changed), correct that row as you go, and promote a confirmed `screen -> API` row back into it.
2. **Bisect by boundaries, not by code.** Walk the chain the data/behavior crosses (UI -> API ->
   queue -> store -> batch -> external) checking the actual artifact at each hop; for
   "stopped accumulating" symptoms compare each hop's last-seen timestamp against the incident
   start. The first boundary where actual != expected is the locus - only then open the code that
   owns it.
3. **Early report checkpoint.** Once broken boundary + direct evidence are in hand, REPORT before deep
   root-causing. Continue deeper only if the user asks or the fix requires it.

## Single-driver default, escalate on breadth

Default: one driver and Reproduce -> Localize -> Fix -> Verify. Escalate only when the fix spans many
files/services (roughly >5 files or cross-service path): one agent localizes, another fixes.

## Distributed triage (cross-boundary bugs)

For DB/API/network/queue failures, map before digging:

1. **Golden signals first.** Frame the symptom in latency, traffic, errors, saturation (RED =
   rate/errors/duration is the request-side subset; USE is the resource side). State *what* is broken
   before guessing *why*; chase only causes that are definite and imminent.
2. **Correlation ID is a precondition.** Cross-service RCA needs a trace/request/correlation ID
   propagated across every boundary. If none exists, say so and make establishing it the first task.
3. **Known-good vs known-bad.** Compare a passing request/trace against a failing one. Find the
   tag/value *unusually* correlated with failures, not ones always present. Recent clustering matters;
   always-clustered is baseline noise.
4. **Failure-pattern checklist.** Before blaming app logic, rule out common distributed traps:
   cascading overload (grows by positive feedback; secondary symptoms mimic the cause), retry storms
   (retries multiply load across layers — needs jittered backoff + per-request limit + retry budget),
   missing deadline propagation (work spent on already-failed requests), partial failure / bimodal
   latency (a few slow requests exhaust upstream pools). Read latency distributions, not averages.

## Loop

1. **Reproduce red (fail-to-pass).** Create a deterministic failing test or scripted repro in a clean
   sandbox (fresh `git worktree` at HEAD). The repro must FAIL on current code and PASS after the fix
   with no new failures (F->P). Scaffold repro explicitly. Flaky/timing/concurrency repros must fail
   consistently over N repeats before trust. Record `run-to-prove`.
2. **Localize.** Narrow the smallest region. Use `git bisect`, input/state binary search, distributed
   triage, and focused instrumentation. Read structure first; load full code only for surviving suspects.
3. **Compete hypotheses (symptom vs cause).** Put 2-3 root causes in `PLAN.md` using a hypothesis
   ledger format: symptom, candidate cause, evidence-for, evidence-against,
   and "definite & imminent?". Phrase each candidate as a falsifiable prediction (if cause C, then
   probe P flips the result) so the most discriminating probe is obvious. Pick the next probe that
   best separates them. Resist fixating on the first plausible cause; advance only causes backed by
   direct evidence.
4. **Confirm.** Before locking the cause, present the 3-5 ranked hypotheses to the user for re-ranking
   (`reference/interview.md` DEBUG variant owns the mechanics: non-blocking, AFK-proceed, never abandon
   evidence for preference). Then back one hypothesis with direct evidence at the boundary. Write the
   fix plan in `PLAN.md`; the plan approval gate (`reference/role-loop.md`) clears before the first
   fix edit.
   If fix blast radius reaches past the cause site, present it with the re-ranking and apply
   `reference/interview.md` before the first edit. Ask only on SKILL.md hard stops or genuine ambiguity.
5. **Fix root cause (minimal diff, checkpoint per step).** Smallest change that addresses cause, not
   symptom. No silencing, fake success, broad refactor, or unrelated cleanup. Checkpoint after each
   plan step so every change traces to one observed outcome; do not free-form edit until green.
6. **Verify regression.** The red repro now passes in a clean sandbox and the full suite stays green.
   This failing-before/passing-after proof is DEBUG's literal delivery evidence.

After Fix, the shared mandatory core still applies: Exact Verify/QA runs fresh-context with its
adversarial stance (`reference/role-loop.md`).

## Circuit breaker

Same error signature 3 times: stop. Record attempts + leading hypothesis in `PLAN.md`, then escalate
with evidence.

## Vault

Every probe result goes to the `PLAN.md` hypothesis ledger. The vault prevents fresh contexts from
re-investigating solved ground.
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