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_check_ccl_regressions.sh

View on GitHub
#!/usr/bin/env bash
# Aggregate deterministic shell regressions for check-ccl-skills wrappers.
#
# Default / local layer: --fast. CI runs the two layers as parallel jobs
# (regression-fast --fast, regression-heavy --heavy-only); --full remains the
# local aggregate (`make test-check-ccl-regressions`). Makefile and CI both call
# this single entrypoint instead of copying test lists.
#
# Usage:
#   bash skills/skill-extraction-workflow/scripts/test_check_ccl_regressions.sh [--fast|--full|--heavy-only]
#
# --fast runs the quick/mid wrapper regressions:
#   - test_ai_coding_implementation_gates.sh
#   - test_locale_independent_gates.sh
#   - test_controlled_escalation_pins.sh
#   - test_teardown_guard_pins.sh
#   - test_check_ccl_size_budget.sh
#   - test_check_ccl_skill_catalog.sh
#   - test_generic_r0_leak_scan.sh
#   - test_shared_git_surface_gate.sh
#   - test_extraction_review_gate.sh
#   - test_check_review_evidence_present.sh
#   - test_check_ccl_route_drift.sh
#   - test_check_sync_pointers.sh
#   - test_check_ccl_register_pending_exclusion.sh
#   - test_eval_routing_bank_grader_diagnostics.sh
#   - test_eval_routing_bank_surface_binding.sh
#   - test_eval_routing_bank_resolution.sh
#   - test_eval_routing_prose_target.sh
#   - test_validate_skill_credential_cwd.sh
#   - test_validate_skill_root_depth.sh
#   - test_regression_runner_registration.sh
#   - test_uiux_delivery_contract.sh
#   - test_uiux_loading_budget.sh
#   - test_obligation_ledger.sh
#   - test_obligation_ledger_repo_audit.sh
#   - test_reference_access_census.sh
# --full runs --fast plus the heavy full-checker regressions:
#   - test_check_ccl_r0_status.sh
#   - test_check_ccl_source_register_lifecycle.sh
#   - test_check_ccl_impact_chain_refscripts.sh
#   - test_register_firing_path_wiring.sh
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
REPO_ROOT="$(git -C "$SCRIPT_DIR" rev-parse --show-toplevel 2>/dev/null || { cd "$SCRIPT_DIR/../../.." && pwd -P; })"
# REGRESSION_SCRIPTS_DIR redirects the whole runner (execution and audit) at a
# fixture tree, so the lane-semantics regression can prove mode dispatch with
# stub suites instead of the real multi-minute ones.
SCRIPTS_DIR="${REGRESSION_SCRIPTS_DIR:-$REPO_ROOT/skills/skill-extraction-workflow/scripts}"

usage() {
  cat <<'EOF'
Usage: test_check_ccl_regressions.sh [--fast|--full|--heavy-only]

Runs deterministic shell regressions for check-ccl-skills wrapper behavior.
Default is --fast to keep local `make test` light. CI runs --fast and
--heavy-only as parallel jobs; --full is the local aggregate.

Modes:
  --fast  the quick/mid wrapper regressions (exact set = the fast_tests array below / the list above)
  --full  fast layer plus R0 status and source-register lifecycle regressions
  --heavy-only  only the heavy full-checker regressions (the heavy_tests array);
          gives CI a heavy execution surface that does not repeat the fast layer
  --list-unregistered  print sibling test_*.sh NOT in fast_tests/heavy_tests (one per
          line) and exit 0; used by the registration guard test so a new test cannot
          silently skip CI. REGRESSION_SCRIPTS_DIR overrides the scanned directory.
EOF
}

mode="fast"
case "${1:-}" in
  ""|--fast) mode="fast" ;;
  --full) mode="full" ;;
  --heavy-only) mode="heavy-only" ;;
  --list-unregistered) mode="list-unregistered" ;;
  -h|--help) usage; exit 0 ;;
  *) usage >&2; exit 2 ;;
esac

if [ "$#" -gt 1 ]; then
  usage >&2
  exit 2
fi

# Lanes execute through the shared bounded-concurrency runner: these suites are
# dominated by waiting (process timeouts, stub sleeps) and by independent
# subprocesses, so serial execution burned wall-clock the runner host was not
# using. The runner owns the missing-file precondition, the per-suite timing
# line, in-order output replay, and failure propagation; assertions inside the
# suites are untouched. `SUITE_JOBS=1` restores serial execution for debugging a
# suspected concurrency interaction. See specs/037-ci-intra-job-parallel/plan.md
# for the per-lane shared-state audit that makes this safe.
PARALLEL_RUNNER="$REPO_ROOT/scripts/run-parallel-suites.sh"

run_lane() {
  local label="$1"; shift
  local paths=() entry
  for entry in "$@"; do paths+=("$SCRIPTS_DIR/$entry"); done
  [ -f "$PARALLEL_RUNNER" ] || {
    echo "FAIL: missing parallel suite runner: $PARALLEL_RUNNER" >&2
    exit 1
  }
  bash "$PARALLEL_RUNNER" --label "$label" "${paths[@]}"
}

fast_tests=(
  test_ai_coding_implementation_gates.sh
  # Gates under a POSIX/unset locale: static pin coverage plus an applied
  # pin-removal mutation, one throwaway fixture, seconds.
  test_locale_independent_gates.sh
  # Reproducible RED-baseline for the controlled-escalation pin family: parses
  # family 8 out of the fixture above and proves each pin reds under its own
  # applied deletion mutation in a throwaway copy (spec 031 review disposition).
  test_controlled_escalation_pins.sh
  # Applied-mutation walk for the worktree teardown guard rows (family 9 of the
  # fixture above) plus decoy surfaces for its sweep; throwaway copy, seconds.
  test_teardown_guard_pins.sh
  test_check_ccl_size_budget.sh
  # Entrypoint guidance-form census (what counts as one rule, a prohibition, a
  # named baseline failure): synthetic fixtures plus the shipped entrypoint,
  # seconds. Pins the definitions, never any round's figures.
  test_entrypoint_form_census.sh
  # Usage census over synthetic transcripts (counts, privacy contract,
  # unevaluated sentinel, ARG_MAX batching): no host logs, seconds.
  test_reference_access_census.sh
  test_check_ccl_skill_catalog.sh
  test_check_mr_target_freshness.sh
  test_generic_r0_leak_scan.sh
  test_shared_git_surface_gate.sh
  test_extraction_review_gate.sh
  # Review-evidence presence gate: own throwaway git repo, seconds.
  test_check_review_evidence_present.sh
  # Candidate-SHA-bound gate receipts (mint/verify): own throwaway git repo,
  # no clone, seconds — belongs in the lane every run exercises.
  test_gate_receipt.sh
  test_check_ccl_route_drift.sh
  test_check_sync_pointers.sh
  test_check_ccl_register_pending_exclusion.sh
  test_register_firing_path_resolution.sh
  # Merge-time containment for the gate's date dependency; the deep three-leg
  # differential stays in the heavy suite, but a require-date regression must
  # go RED in every `make test`, not only under --full.
  test_impact_chain_gate_dateless_host.sh
  # Row-ownership attribution probes: a control leg plus the refusals the gate
  # owes on a surviving row that vouches for an unchanged owner, a row citing a
  # package path other than SKILL.md, a row resolving to two selected owners,
  # and the two shapes that must keep their prior silent skip (an unrelated
  # five-column register table, a non-curated owner). Synthetic repos only, no
  # clone, so it belongs in the lane every run exercises.
  test_impact_chain_round_attribution.sh
  test_eval_routing_bank_grader_diagnostics.sh
  test_eval_routing_bank_surface_binding.sh
  test_eval_routing_bank_resolution.sh
  test_eval_routing_prose_target.sh
  test_validate_skill_credential_cwd.sh
  test_validate_skill_root_depth.sh
  test_validate_skill_cross_refs.sh
  test_git_identity_predicate_gate.sh
  test_liveness_predicate_gate.sh
  # 074: contract-anchor gate self-proof (tmp fixtures + one real-repo leg,
  # seconds) and the anti-patterns panel structural check (awk over one file).
  test_check_contract_anchors.sh
  test_antipattern_grep_panel.sh
  # 075: body-compliance grading contract (grade() walk, fail-closed --ids legs,
  # stub-model denominator/forbidden_hit legs; deterministic, seconds).
  test_body_compliance_grading.sh
  test_regression_runner_registration.sh
  # Harness binding for the gate lanes themselves: the impact-chain gate's
  # round walk needs the branch's own first-parent chain, which the default
  # refs/pull/N/merge checkout does not provide. Cheap, no clone, and a
  # regression here is otherwise invisible until it refuses an unrelated PR.
  test_ci_checkout_ref_binding.sh
  # Lane-semantics guard for this runner itself (036 challenge P2): proves
  # --heavy-only / --fast / --full each run exactly their lane against a stub
  # fixture via REGRESSION_SCRIPTS_DIR, and that a red heavy stub propagates.
  test_regression_runner_lanes.sh
  test_routing_pointer_integrity.sh
  test_routing_bank_integrity.sh
  # 077: frozen-case sanctity (regressions-are-sacred) — base-relative guard
  # that a deleted/re-scoped bank case or golden trace names its adjudication
  # row; degrades to an explicit skip token without CCL_SKILL_BASE_REF. The
  # selfproof lane proves the oracle fails for the right reason (synthetic
  # repo: deletion/re-scope/nested-trace mutants red, forged-credit legs red,
  # adjudicated and control legs green).
  test_frozen_case_sanctity.sh
  test_frozen_case_sanctity_selfproof.sh
  test_uiux_delivery_contract.sh
  test_uiux_loading_budget.sh
  test_governing_chain_diff.sh
  test_obligation_ledger.sh
  # Audits the REAL specs/065 mapping and ledger against the base and head
  # pinned in the ledger header, catching carrier drift the synthetic fixtures
  # above cannot see: any edit that moves a cited line in skills/**/*.md makes
  # the ledger stale. It needs full history (the CI fast job checks out with
  # fetch-depth 0) and takes seconds, so it runs here, where `make test` and the
  # fast CI job reach it before a push, not only in the heavy lane.
  test_obligation_ledger_repo_audit.sh
  # Owned by another skill package; run_test resolves it relative to SCRIPTS_DIR.
  # Registered here because this runner is the repo's only regression lane —
  # a skill-local test left unregistered is the false-green this file guards.
  ../../testing-strategy/scripts/test_mutation_backup_recipe.sh
)

heavy_tests=(
  test_check_ccl_r0_status.sh
  test_entrypoint_domain_scan_terms.sh
  test_check_ccl_source_register_lifecycle.sh
  # Clones the whole repo once; impact-chain cases call the standalone gate and
  # retain one full-checker wiring case. Still kept out of the pre-commit lane.
  test_check_ccl_impact_chain_refscripts.sh
  # Same reason: clones the repo and drives the full checker TWICE (~26s, the
  # slowest entry the lane had). Its sibling
  # `test_register_firing_path_resolution.sh` keeps the gate's behaviour in the
  # fast lane; this one only proves the checker WIRING, which cannot drift from a
  # local edit without also changing the checker. CI runs `--full`, so moving it
  # here costs no enforcement — it only stops charging every pre-commit run for a
  # repo clone, and stops a slow entry competing for the runner host.
  test_register_firing_path_wiring.sh
  # No-verdict-regression differential: materializes twelve pinned integration
  # points as detached worktrees and runs both the baseline and candidate gate
  # against each. Proves the other half of a gate change — that it did not start
  # refusing what it used to accept — which is the half that blocks every author
  # when it goes wrong. Worktree-per-point makes it far too slow for pre-commit.
  # source-refuted 证据类的滥用面:16 条合成用例,每条一条分支,且整仓 clone 一次
  # 作 fixture 底座。它测的正是「这个类会不会变成通用豁免」——七轮独立评审各击穿过
  # 一版门槛,所以负向用例(真行为变更披标签、抵消式新增、路径穿越、子串锚、改权限、
  # 对照表不交代被删内容)必须每轮都跑。clone + 16 分支对 pre-commit 太慢,进 heavy。
  test_impact_chain_source_refuted.sh
  test_impact_chain_gate_verdict_differential.sh
  # 045:两个触发器(routing 面改动欠 bank 证据、台账行欠 result-class)的十条决策表
  # 用例。同样是整仓 clone + 一 case 一分支的形态,故与上面两套同进 heavy。它钉的是
  # 「跳过义务会不会留下可检出的缺席」——044 连续五轮 challenge 都停在这一点上,负向
  # 用例(缺证据、非枚举值、降范围无留痕)必须每轮都跑,否则触发器会悄悄退化成声称。
  test_impact_chain_self_adjudication.sh
  # 074: one applied deletion mutation per pinned-phrase gate family, each leg
  # running the FULL shipped checker against a committed fixture copy of the
  # working tree (6 full-gate runs — far too slow for pre-commit). Proves the
  # ~40 required_phrase pins and the contract-anchor delegation can actually
  # go red for the right reason; the fast lane keeps the checker-level
  # self-proof in test_check_contract_anchors.sh.
  test_pinned_phrase_mutation_walk.sh
)

# Registration self-audit: every sibling test_*.sh must appear in fast_tests or
# heavy_tests, else CI silently skips it (a false-green — the class that let
# test_validate_skill_credential_cwd.sh ship unrun). Compute the gap here so both
# --list-unregistered (for the guard test) and the normal-run advisory share it.
# REGRESSION_SCRIPTS_DIR overrides the scanned dir so the guard test can point at
# a fixture. Bash 3.2-safe (string-set membership, no associative arrays).
self_name="$(basename "$0")"
audit_dir="${REGRESSION_SCRIPTS_DIR:-$SCRIPTS_DIR}"
registered=" ${fast_tests[*]} ${heavy_tests[*]} "
unregistered=""
for audit_f in "$audit_dir"/test_*.sh; do
  [ -e "$audit_f" ] || continue           # literal glob when no match
  audit_b="$(basename "$audit_f")"
  [ "$audit_b" = "$self_name" ] && continue   # the runner never registers itself
  case "$registered" in *" $audit_b "*) continue ;; esac
  unregistered="$unregistered $audit_b"
done
unregistered="${unregistered# }"

if [ "$mode" = "list-unregistered" ]; then
  [ -n "$unregistered" ] && printf '%s\n' $unregistered
  exit 0
fi

# Unregistered siblings hard-fail every execution mode (036 challenge P1): the
# old advisory-only tail made enforcement depend on the registration guard test
# itself staying registered — removing it from fast_tests silenced the only red
# path. Failing here keeps enforcement independent of any one array entry.
if [ -n "$unregistered" ]; then
  echo "FAIL: test_*.sh not registered in fast_tests/heavy_tests (CI would silently skip them):$unregistered" >&2
  exit 1
fi

if [ "$mode" != "heavy-only" ]; then
  run_lane regression_fast_lane "${fast_tests[@]}"
fi

if [ "$mode" = "full" ] || [ "$mode" = "heavy-only" ]; then
  run_lane regression_heavy_lane "${heavy_tests[@]}"
fi

case "$mode" in
  full) echo "test_check_ccl_regressions_full_ok" ;;
  heavy-only) echo "test_check_ccl_regressions_heavy_only_ok" ;;
  *) echo "test_check_ccl_regressions_fast_ok" ;;
esac
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