Skip to content

ccoalm/ccl-skills / skills/skill-extraction-workflow

skill-extraction-workflow

Flagged

复盘 / 沉淀 / 总结经验 / 补进技能 / 技能缺陷 / 流程优化 / would other teammates hit this / will we forget next time / teamwide recurrence / extract skill / post-mortem / 深度 review·审计技能仓库 / 对标外部技能包找 gap(benchmark superpowers·gstack 等) / 核查全局安装点(~/.config/opencode 等)旧快照是否遮蔽本仓技能 / 本仓(ccl-skills 等共享技能仓)OpenCode 项目配置·命令治理 → turn reusable lessons into durable CCL skills.

FileKindSize
SKILL.mdskill md111.0 KB
agents/openai.yamlconfig257 B
references/analysis-parse-fix-test-challenge-replay.mdmarkdown1.5 KB
references/attention-budget-ratchet.mdmarkdown13.7 KB
references/attribution-verification.mdmarkdown4.4 KB
references/bootstrap-slim-c3-obligation-table.mdmarkdown8.0 KB
references/correction-routing-map.mdmarkdown3.7 KB
references/coverage-exhaustion-traps.mdmarkdown19.6 KB
references/description-authoring.mdmarkdown21.1 KB
references/dual-track-review-gate.mdmarkdown110.6 KB
references/eval-routing.mdmarkdown22.2 KB
references/evidence-card-template.mdmarkdown3.2 KB
references/example-domain-preselect.mdmarkdown4.6 KB
references/external-practice-controls.mdmarkdown45.5 KB
references/extraction-lifecycle-handoff.mdmarkdown6.9 KB
references/extraction-quickstart.mdmarkdown20.2 KB
references/firing-point-placement.mdmarkdown21.3 KB
references/harness-patterns-and-eval.mdmarkdown42.6 KB
references/incident-postmortem-extraction.mdmarkdown28.8 KB
references/l0-l1-l2-routing.mdmarkdown10.3 KB
references/online-skill-review.mdmarkdown6.7 KB
references/parallel-stack-references-pattern.mdmarkdown35.9 KB
references/r0-leakage-audit.mdmarkdown19.9 KB
references/recurring-anti-patterns-checklist.mdmarkdown34.4 KB
references/resume-paused-delivery.mdmarkdown3.0 KB
references/review-feedback-mining.mdmarkdown5.7 KB
references/review-finding-standards.mdmarkdown7.3 KB
references/review-rubric.mdmarkdown3.1 KB
references/rule-consolidation.mdmarkdown38.2 KB
references/skill-listing-budget.mdmarkdown1.7 KB
references/source-register.mdmarkdown1.0 MB
references/source-to-skill-extraction.mdmarkdown109.3 KB
references/two-source-extraction-pattern.mdmarkdown19.4 KB
references/uiux-judgment-extraction.mdmarkdown19.1 KB
references/uiux-routing-map.mdmarkdown5.8 KB
references/validation-and-landing.mdmarkdown46.9 KB
scripts/AGENTS.mdmarkdown635 B
scripts/check-ccl-skills.shexecutablescript100.7 KB
scripts/check-contract-anchors.shexecutablescript5.6 KB
scripts/check-evidence-card-leak.shexecutablescript26.1 KB
scripts/check-mr-target-freshness.shexecutablescript9.4 KB
scripts/check-size-budget.shexecutablescript36.0 KB
scripts/check-sync-pointers.shexecutablescript22.6 KB
scripts/check_review_evidence_present.pyexecutablescript4.6 KB
scripts/contract-anchors.tsvother3.8 KB
scripts/entrypoint_form_census.pyexecutablescript7.1 KB
scripts/eval-golden-trace.rbexecutablescript10.0 KB
scripts/eval-health.rbexecutablescript14.6 KB
scripts/eval-routing-bank.rbexecutablescript30.4 KB
scripts/eval-routing.rbexecutablescript9.2 KB
scripts/extraction_review_gate.shexecutablescript1.8 KB
scripts/gate_receipt.pyexecutablescript24.7 KB
scripts/generic-r0-leak-scan.shexecutablescript12.4 KB
scripts/governing-chain-diff.pyexecutablescript12.8 KB
scripts/impact-chain-gate.rbexecutablescript124.4 KB
scripts/obligation-ledger.pyscript107.0 KB
scripts/reference-access-census.shexecutablescript8.3 KB
scripts/register-firing-path-resolution.rbexecutablescript48.4 KB
scripts/shared_git_surface_gate.pyexecutablescript38.0 KB
scripts/skill-behavior-eval.pyexecutablescript39.3 KB
scripts/skill-paired-eval.pyexecutablescript76.9 KB
scripts/source-register-lifecycle.rbscript1.5 KB
scripts/source-register-pending-status.rbscript2.0 KB
scripts/test_ai_coding_implementation_gates.shexecutablescript85.2 KB
scripts/test_antipattern_grep_panel.shexecutablescript3.2 KB
scripts/test_body_compliance_grading.shexecutablescript21.0 KB
scripts/test_check_ccl_impact_chain_refscripts.shexecutablescript145.1 KB
scripts/test_check_ccl_r0_status.shexecutablescript4.2 KB
scripts/test_check_ccl_register_pending_exclusion.shexecutablescript7.4 KB
scripts/test_check_ccl_regressions.shexecutablescript14.3 KB
scripts/test_check_ccl_route_drift.shexecutablescript22.6 KB
scripts/test_check_ccl_size_budget.shexecutablescript59.5 KB
scripts/test_check_ccl_skill_catalog.shexecutablescript23.3 KB
scripts/test_check_ccl_source_register_lifecycle.shexecutablescript6.1 KB
scripts/test_check_contract_anchors.shexecutablescript7.4 KB
scripts/test_check_mr_target_freshness.shexecutablescript12.8 KB
scripts/test_check_review_evidence_present.shexecutablescript4.3 KB
scripts/test_check_sync_pointers.shexecutablescript32.5 KB
scripts/test_ci_checkout_ref_binding.shexecutablescript8.2 KB
scripts/test_controlled_escalation_pins.shexecutablescript7.7 KB
scripts/test_entrypoint_domain_scan_terms.shexecutablescript8.8 KB
scripts/test_entrypoint_form_census.shexecutablescript6.3 KB
scripts/test_eval_routing_bank_grader_diagnostics.shexecutablescript20.6 KB
scripts/test_eval_routing_bank_resolution.shexecutablescript15.3 KB
scripts/test_eval_routing_bank_surface_binding.shexecutablescript6.9 KB
scripts/test_eval_routing_prose_target.shexecutablescript3.7 KB
scripts/test_eval_runtime.pyexecutablescript43.3 KB
scripts/test_extraction_review_gate.shexecutablescript15.2 KB
scripts/test_frozen_case_sanctity.shexecutablescript6.9 KB
scripts/test_frozen_case_sanctity_selfproof.shexecutablescript4.6 KB
scripts/test_gate_receipt.shexecutablescript17.7 KB
scripts/test_generic_r0_leak_scan.shexecutablescript6.4 KB
scripts/test_git_identity_predicate_gate.shscript13.8 KB
scripts/test_governing_chain_diff.shexecutablescript15.1 KB
scripts/test_impact_chain_gate_dateless_host.shexecutablescript6.8 KB
scripts/test_impact_chain_gate_verdict_differential.shexecutablescript20.8 KB
scripts/test_impact_chain_round_attribution.shexecutablescript32.5 KB
scripts/test_impact_chain_self_adjudication.shexecutablescript31.4 KB
scripts/test_impact_chain_source_refuted.shexecutablescript14.7 KB
scripts/test_liveness_predicate_gate.shexecutablescript14.5 KB
scripts/test_locale_independent_gates.shexecutablescript13.0 KB
scripts/test_obligation_ledger.shexecutablescript94.9 KB
scripts/test_obligation_ledger_repo_audit.shexecutablescript2.7 KB
scripts/test_pinned_phrase_mutation_walk.shexecutablescript6.5 KB
scripts/test_reference_access_census.shexecutablescript17.3 KB
scripts/test_register_firing_path_resolution.shexecutablescript41.0 KB
scripts/test_register_firing_path_wiring.shexecutablescript29.9 KB
scripts/test_regression_runner_lanes.shexecutablescript4.5 KB
scripts/test_regression_runner_registration.shexecutablescript1.5 KB
scripts/test_routing_bank_integrity.shexecutablescript15.5 KB
scripts/test_routing_pointer_integrity.shexecutablescript18.9 KB
scripts/test_shared_git_surface_gate.shexecutablescript76.8 KB
scripts/test_skill_paired_eval.pyscript60.0 KB
scripts/test_teardown_guard_pins.shexecutablescript17.0 KB
scripts/test_uiux_delivery_contract.shexecutablescript118.6 KB
scripts/test_uiux_loading_budget.shexecutablescript15.4 KB
scripts/test_validate_skill_credential_cwd.shexecutablescript2.6 KB
scripts/test_validate_skill_cross_refs.shexecutablescript4.8 KB
scripts/test_validate_skill_root_depth.shexecutablescript2.5 KB
scripts/validate-skill.shexecutablescript10.5 KB

scripts/test_routing_bank_integrity.sh

View on GitHub
#!/usr/bin/env bash
# Structural contract test for the routing task bank (eval/routing-tasks.jsonl).
#
# SCOPE — read this before citing the lane as evidence. This test proves the
# bank is well-formed and that every skill it names actually exists. It does
# NOT route anything and therefore does NOT prove any fixture's expectation is
# delivered: the behavioural grader (`eval-routing-bank.rb`) shells out to a
# live `claude` CLI, so it is advisory Tier-2 and cannot be a deterministic CI
# gate. A source-register row may cite THIS lane for "the fixture exists, is
# well-formed, and its targets resolve" — never for "the fixture passes".
#
# What it catches (the gap it was written for): a fixture silently deleted,
# an id collision, a typo'd or renamed target skill, a required provenance
# field dropped, or a self-contradictory row. Before this lane existed, all of
# those stayed green because the only registered routing lane checks literal
# phrases in SKILL.md files and never opens the bank at all.
set -u
ROOT="${BANK_ROOT:-$(cd "$(dirname "$0")/../../.." && pwd)}"
[ -n "${BANK_ROOT:-}" ] && echo "NOTICE: BANK_ROOT set — testing tree: $ROOT" >&2
BANK="$ROOT/eval/routing-tasks.jsonl"

if [ ! -f "$BANK" ]; then
  echo "FAIL: task bank missing ($BANK)" >&2
  exit 1
fi

python3 - "$ROOT" "$BANK" <<'PY'
import json, os, sys

root, bank = sys.argv[1], sys.argv[2]
skills_dir = os.path.join(root, "skills")
installed = {
    name for name in os.listdir(skills_dir)
    if os.path.isfile(os.path.join(skills_dir, name, "SKILL.md"))
}

# Universal fields, measured against the bank rather than assumed: all 113 rows
# carry these five. `source` is present on only 37/113 and `added_by_change_sha`
# on none, although docs/f4-skill-effectiveness-harness.md lists both as required
# provenance — that doc-vs-bank drift is reported below, not failed, because
# failing it would red-line ~76 pre-existing rows this change never touched.
REQUIRED = ("id", "utterance", "expected_skill", "why_expected", "frozen_at_sha")
fail = 0
seen = {}
rows = 0

def bad(msg):
    global fail
    print(f"FAIL: {msg}", file=sys.stderr)
    fail = 1

with open(bank, encoding="utf-8") as fh:
    for lineno, raw in enumerate(fh, 1):
        raw = raw.strip()
        if not raw:
            continue
        rows += 1
        try:
            row = json.loads(raw)
        except json.JSONDecodeError as exc:
            bad(f"line {lineno}: not valid JSON ({exc})")
            continue

        rid = row.get("id")
        for field in REQUIRED:
            if not row.get(field):
                bad(f"line {lineno} ({rid}): missing/empty required field '{field}'")

        if rid in seen:
            bad(f"line {lineno}: duplicate id '{rid}' (first seen line {seen[rid]})")
        elif rid:
            seen[rid] = lineno

        # "none" is the runner's negative-control / coverage-gap sentinel
        # (eval-routing-bank.rb): the expected outcome is that no catalog skill
        # claims the utterance. It is an outcome, never a routable target.
        expected = row.get("expected_skill")
        if expected and expected != "none" and expected not in installed:
            bad(f"line {lineno} ({rid}): expected_skill '{expected}' is not a skill in skills/")

        # Type-check the ORIGINAL value: `x or []` would first convert an
        # explicitly invalid "" (or 0/false) into a clean empty list, so the
        # deterministic lane would pass a row the Ruby runner rejects.
        must_not = row.get("must_not_route_to")
        if must_not is None:
            must_not = []
        elif not isinstance(must_not, list):
            bad(f"line {lineno} ({rid}): must_not_route_to must be a list, got {must_not!r}")
            must_not = []
        for target in must_not:
            if target == "none":
                bad(f"line {lineno} ({rid}): must_not_route_to names the sentinel 'none' (an outcome, not a routable target)")
            elif target not in installed:
                bad(f"line {lineno} ({rid}): must_not_route_to names '{target}', not a skill in skills/")
            if target == expected:
                bad(f"line {lineno} ({rid}): '{target}' is both expected_skill and must_not_route_to")

        acceptable = row.get("acceptable")
        if acceptable is None:
            acceptable = []
        elif not isinstance(acceptable, list):
            bad(f"line {lineno} ({rid}): acceptable must be a list, got {acceptable!r}")
            acceptable = []
        for target in acceptable:
            if target != "none" and target not in installed:
                bad(f"line {lineno} ({rid}): acceptable names '{target}', not a skill in skills/ (nor the 'none' sentinel)")
            if target == expected:
                bad(f"line {lineno} ({rid}): '{target}' is both expected_skill and acceptable (redundant)")
            if target in must_not:
                bad(f"line {lineno} ({rid}): '{target}' is both acceptable and must_not_route_to (contradictory)")

        # Anti-gaming mirror of the runner's vacuous-row rule: expected +
        # acceptable must leave at least one outcome that would fail the row,
        # or every valid grader selection passes and the fixture fakes green.
        if isinstance(acceptable, list) and expected:
            outcome_space = set(installed) | {"none"}
            if not outcome_space - ({expected} | set(acceptable)):
                bad(f"line {lineno} ({rid}): expected_skill plus acceptable cover every possible outcome (vacuous row)")

# A truncated or emptied bank must fail rather than vacuously pass.
MIN_ROWS = 100
if rows < MIN_ROWS:
    bad(f"bank has {rows} rows, expected at least {MIN_ROWS} (truncation guard)")

# Row-count guards are too coarse to notice ONE deleted fixture (deleting one of
# 113 still clears MIN_ROWS). Any fixture a source-register row cites as its
# evidence is pinned by id here, so removing it turns this lane red instead of
# silently invalidating the row that points at it. Add an id when a new register
# row cites a new fixture, in the same diff.
CITED_BY_REGISTER_ROWS = (
    "miss-refactor-python-unqualified",
    "miss-refactor-miniapp",
    "route-python-cli-not-terminal",
    "route-go-cli-not-terminal",
    "route-cli-contract-design-not-stack",
)
for rid in CITED_BY_REGISTER_ROWS:
    if rid not in seen:
        bad(f"fixture '{rid}' is cited by a source-register row but is absent from the bank")

# frozen_at_sha ancestry. docs/f4-skill-effectiveness-harness.md says the runner
# validates this, but the runner needs a live model and no committed-time lane
# checked it — so a fixture carrying a sha from an unrelated history (the "drift"
# the field exists to catch) reached main unchallenged. Verified here instead.
#
# SEMANTICS, because two readers already read this field two different ways:
# frozen_at_sha is an ANCESTRY/BATCH marker, not a claim that the expectation was
# already deliverable at that commit. Fixtures that land together share the sha
# of the branch point, so a fixture added ALONGSIDE the routing surface it
# describes is correctly frozen at a commit where that surface does not yet
# exist. Do not "fix" such a row by pointing it at a post-landing commit: branch
# shas do not survive a squash merge, and a dangling sha reads as drift and
# silently drops the fixture from regression judgement.
import subprocess

def git(*args):
    return subprocess.run(("git", "-C", root) + args,
                          capture_output=True, text=True)


if git("rev-parse", "--git-dir").returncode != 0:
    print("routing_bank_ancestry_info: not a git checkout — ancestry not verified")
else:
    # An unresolvable sha is tolerated ONLY where it is genuinely explainable:
    # a shallow or partial clone that simply does not carry the object. In a
    # COMPLETE checkout an unresolvable sha means the row points at a mistyped,
    # dangling, or unrelated history — which is precisely the drift this check
    # exists to catch, and the row would be silently dropped from regression
    # judgement. Tolerating it unconditionally made the lane pass in exactly the
    # case it was written for.
    # Shallow detection: ONE signal, the `shallow` marker file. It is the ground
    # truth `--is-shallow-repository` itself derives from, so pairing the two as
    # "primary + fallback" is not redundancy — whichever is second is provably
    # unreachable, and shipping an unreachable branch is how you get code that
    # has never been observed to work. Verified both ways: deleting the marker
    # makes the porcelain report false too.
    #
    # --git-COMMON-dir, not --git-dir: in a linked worktree --git-dir returns
    # .git/worktrees/<name>, while `shallow` lives in the shared .git — probing
    # the per-worktree dir silently finds nothing and reports every shallow
    # worktree as a complete checkout.
    common_dir = git("rev-parse", "--git-common-dir").stdout.strip()
    shallow = False
    if common_dir:
        cd_abs = common_dir if os.path.isabs(common_dir) else os.path.join(root, common_dir)
        shallow = os.path.isfile(os.path.join(cd_abs, "shallow"))
    # Partial clone: git marks the PROMISOR REMOTE, whose name is not necessarily
    # "origin" (`git clone -o upstream --filter=...`). Scan every remote, or a
    # partial clone under any other remote name gets red-lined on every row.
    # `extensions.partialClone` is the repository-level marker (it names the
    # promisor remote) and survives a remote rename; the per-remote keys are the
    # corroborating signal. Check both, under any remote name.
    partial = bool(git("config", "--get", "extensions.partialClone").stdout.strip()) or \
        bool(git("config", "--get-regexp",
                 r"^remote\..*\.(promisor|partialclonefilter)$").stdout.strip())
    # ONE decision point, deliberately hoisted out of the per-sha loop.
    #
    # This used to be consulted twice INSIDE the loop — once for an unresolvable
    # object, once for a failed ancestry query — and both times I added a new
    # failure mode while guarding only one of the two exits. A degraded clone
    # cannot answer either question, so the honest structure is to decide once,
    # up front, whether ancestry is answerable at all. Adding a third git query
    # later cannot reintroduce the bug: there is no per-query tolerance to forget.
    degraded = shallow or partial
    if degraded:
        kind = "shallow" if shallow else "partial"
        print(f"routing_bank_ancestry_info: {kind} clone — ancestry NOT verified for any row "
              f"(a complete checkout verifies every row and fails on drift)")
    else:
        for rid, sha in sorted({r.get("id"): r.get("frozen_at_sha") for r in
                                [json.loads(l) for l in open(bank, encoding="utf-8") if l.strip()]}.items()):
            if not sha:
                continue  # empty/missing is already a required-field failure above
            if sha == "root":
                sha = git("rev-list", "--max-parents=0", "HEAD").stdout.splitlines()[0]
            if git("cat-file", "-e", f"{sha}^{{commit}}").returncode != 0:
                bad(f"({rid}): frozen_at_sha {sha[:12]} does not resolve to a commit in this "
                    f"complete checkout (mistyped or from an unrelated history — the row would "
                    f"be silently excluded from regression judgement)")
                continue
            if git("merge-base", "--is-ancestor", sha, "HEAD").returncode != 0:
                bad(f"({rid}): frozen_at_sha {sha[:12]} is not an ancestor of HEAD (drift — the "
                    f"row would be silently excluded from regression judgement)")
        print(f"routing_bank_ancestry_ok: {rows} row(s) verified against HEAD")

if fail:
    sys.exit(1)

# Informational: provenance coverage the harness doc asks for but the bank does
# not yet carry. Reported so the drift stays visible without blocking.
with open(bank, encoding="utf-8") as fh:
    parsed = [json.loads(l) for l in fh if l.strip()]
with_source = sum(1 for r in parsed if r.get("source"))
print(f"routing_bank_provenance_info: source present on {with_source}/{rows} rows "
      f"(docs/f4-skill-effectiveness-harness.md lists it as required; not enforced here)")
print(f"routing_bank_integrity_ok rows={rows} (structure only — routing NOT evaluated)")
PY
main_rc=$?
[ "$main_rc" -eq 0 ] || exit "$main_rc"

# --- validator self-proof (oracle-can-fail) ----------------------------------
# A green main run proves nothing about the new field predicates unless the
# validator is also seen to RED on applied mutants. Run this same script once
# against a synthetic root carrying one mutant per predicate, and require both
# the non-zero exit and each predicate's own FAIL message. Guarded against
# recursion: the inner invocation skips this section.
if [ -z "${BANK_INTEGRITY_SELFPROOF:-}" ]; then
  SP_ROOT="$(mktemp -d "${TMPDIR:-/tmp}/bank-integrity-selfproof.XXXXXX")"
  trap 'rm -rf "$SP_ROOT"' EXIT
  mkdir -p "$SP_ROOT/skills/testing-strategy" "$SP_ROOT/skills/tighten-doc" "$SP_ROOT/eval"
  printf -- '---\ndescription: stub\n---\n' > "$SP_ROOT/skills/testing-strategy/SKILL.md"
  printf -- '---\ndescription: stub\n---\n' > "$SP_ROOT/skills/tighten-doc/SKILL.md"
  cat > "$SP_ROOT/eval/routing-tasks.jsonl" <<'MUTANTS'
{"id": "bad-mustnot-none", "utterance": "x", "expected_skill": "testing-strategy", "why_expected": "y", "frozen_at_sha": "root", "must_not_route_to": ["none"]}
{"id": "bad-acc-restate", "utterance": "x", "expected_skill": "testing-strategy", "why_expected": "y", "frozen_at_sha": "root", "acceptable": ["testing-strategy"]}
{"id": "bad-acc-unknown", "utterance": "x", "expected_skill": "testing-strategy", "why_expected": "y", "frozen_at_sha": "root", "acceptable": ["not-a-skill"]}
{"id": "bad-acc-contradict", "utterance": "x", "expected_skill": "testing-strategy", "why_expected": "y", "frozen_at_sha": "root", "acceptable": ["tighten-doc"], "must_not_route_to": ["tighten-doc"]}
{"id": "bad-acc-empty-string", "utterance": "x", "expected_skill": "testing-strategy", "why_expected": "y", "frozen_at_sha": "root", "acceptable": ""}
{"id": "bad-mustnot-empty-string", "utterance": "x", "expected_skill": "testing-strategy", "why_expected": "y", "frozen_at_sha": "root", "must_not_route_to": ""}
{"id": "bad-none-typo", "utterance": "x", "expected_skill": "not-a-skill", "why_expected": "y", "frozen_at_sha": "root"}
{"id": "bad-universal-pass", "utterance": "x", "expected_skill": "testing-strategy", "why_expected": "y", "frozen_at_sha": "root", "acceptable": ["tighten-doc", "none"]}
MUTANTS
  sp_out="$(BANK_INTEGRITY_SELFPROOF=1 BANK_ROOT="$SP_ROOT" bash "$0" 2>&1)"
  sp_rc=$?
  if [ "$sp_rc" -eq 0 ]; then
    echo "FAIL: validator self-proof — the mutant bank exited 0 (the oracle cannot fail)" >&2
    exit 1
  fi
  for expect in \
    "bad-mustnot-none): must_not_route_to names the sentinel 'none'" \
    "bad-acc-restate): 'testing-strategy' is both expected_skill and acceptable" \
    "bad-acc-unknown): acceptable names 'not-a-skill'" \
    "bad-acc-contradict): 'tighten-doc' is both acceptable and must_not_route_to" \
    "bad-acc-empty-string): acceptable must be a list, got ''" \
    "bad-mustnot-empty-string): must_not_route_to must be a list, got ''" \
    "bad-none-typo): expected_skill 'not-a-skill' is not a skill in skills/" \
    "bad-universal-pass): expected_skill plus acceptable cover every possible outcome (vacuous row)"; do
    case "$sp_out" in
      *"$expect"*) : ;;
      *) echo "FAIL: validator self-proof — expected mutant message not found: $expect" >&2
         echo "$sp_out" >&2
         exit 1 ;;
    esac
  done
  echo "routing_bank_validator_selfproof_ok: 8 applied mutants red on their own assertions"
fi
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