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_contract_anchors.sh

View on GitHub
#!/usr/bin/env bash
# Self-proof suite for check-contract-anchors.sh.
#
# Oracle self-proof tables (the gate is trusted only because every row below
# was APPLIED and observed):
#
# MUST-HIT (mutant -> expected red token, expected rc):
#   M1 pinned literal deleted from anchored file  -> contract_anchor_missing        rc 1
#   M2 pinned literal duplicated in anchored file -> contract_anchor_duplicate      rc 1
#   M3 anchored file removed                      -> contract_anchor_file_missing   rc 1
#   M4 table emptied (comments only)              -> contract_anchor_table_empty    rc 2
#   M5 malformed row (3 fields)                   -> contract_anchor_row_malformed  rc 2
#   M6 literal under 16 chars                     -> contract_anchor_literal_too_short rc 2
#   M7 duplicate anchor id                        -> contract_anchor_duplicate_id   rc 2
#   M8 table file missing                         -> contract_anchor_table_missing  rc 2
#   M9 malformed row + drifted anchor in one table -> BOTH reported, rc 2
#      (integrity errors are collected, well-formed rows still evaluated,
#       and a broken table yields no verdict — fail-closed over the drift)
#
# MUST-NOT-HIT (benign neighbor -> stays green, rc 0):
#   B1 wording adjacent to the pinned literal edited (same line, outside the pin)
#   B2 unrelated file in the tree edited freely
#   B3 anchored file grows new content elsewhere
#
# DIFFERENTIAL ATTRIBUTION:
#   D1 two anchors, one broken -> output names exactly the broken id, rc 1,
#      and the healthy id is not reported
#
# REAL-REPO LEG:
#   R1 shipped table against the repo root -> rc 0 and pinned output grammar
#      "contract_anchor_gate_ok (<N> anchors)"
set -u

script_dir=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd -P)
checker="$script_dir/check-contract-anchors.sh"
repo_root=$(cd "$script_dir/../../.." && pwd -P)
fail=0

note() { printf '%s\n' "$*"; }
expect() { # expect <case> <want_rc> <got_rc> <want_token> <output>
  local case_id="$1" want_rc="$2" got_rc="$3" want_token="$4" output="$5"
  if [[ "$got_rc" -ne "$want_rc" ]]; then
    note "FAIL $case_id: rc=$got_rc want=$want_rc"
    note "$output"
    fail=1
    return
  fi
  if [[ -n "$want_token" && "$output" != *"$want_token"* ]]; then
    note "FAIL $case_id: missing token '$want_token' in output"
    note "$output"
    fail=1
    return
  fi
  note "ok $case_id"
}

tmp=$(mktemp -d)
trap 'rm -rf "$tmp"' EXIT

make_fixture() { # rebuild a fresh fixture tree + table under $tmp/fx
  rm -rf "$tmp/fx"
  mkdir -p "$tmp/fx/docs"
  cat > "$tmp/fx/docs/sample-contract.md" <<'MD'
# Sample contract

The sample verdict is decided by exactly one discriminating predicate here.
Unrelated surrounding prose that may change freely.
MD
  cat > "$tmp/fx/docs/other.md" <<'MD'
Free-floating document with no anchors at all.
MD
  printf '%s\t%s\t%s\t%s\n' \
    "sample-discriminator" "docs/sample-contract.md" \
    "decided by exactly one discriminating predicate" "fixture row" \
    > "$tmp/fx/anchors.tsv"
}

run() { # run <root> <table>; sets got_rc/got_out
  got_out=$(bash "$checker" "$1" --table "$2" 2>&1)
  got_rc=$?
}

# R1: shipped table against the real repo
run "$repo_root" "$script_dir/contract-anchors.tsv"
expect R1 0 "$got_rc" "contract_anchor_gate_ok (" "$got_out"
if ! grep -qE '^contract_anchor_gate_ok \([0-9]+ anchors\)$' <<<"$got_out"; then
  note "FAIL R1-grammar: green output grammar drifted: $got_out"
  fail=1
else
  note "ok R1-grammar"
fi

# Green fixture control (precondition for every mutant below)
make_fixture
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect C0 0 "$got_rc" "contract_anchor_gate_ok (1 anchors)" "$got_out"

# M1 literal deleted
make_fixture
perl -pi -e 's/decided by exactly one discriminating predicate/decided case by case/' "$tmp/fx/docs/sample-contract.md"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect M1 1 "$got_rc" "contract_anchor_missing: sample-discriminator" "$got_out"

# M2 literal duplicated
make_fixture
printf '\nA second copy: decided by exactly one discriminating predicate.\n' >> "$tmp/fx/docs/sample-contract.md"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect M2 1 "$got_rc" "contract_anchor_duplicate: sample-discriminator" "$got_out"

# M3 anchored file removed
make_fixture
rm "$tmp/fx/docs/sample-contract.md"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect M3 1 "$got_rc" "contract_anchor_file_missing: sample-discriminator" "$got_out"

# M4 table emptied
make_fixture
printf '# only comments\n\n' > "$tmp/fx/anchors.tsv"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect M4 2 "$got_rc" "contract_anchor_table_empty" "$got_out"

# M5 malformed row
make_fixture
printf 'bad-row\tdocs/sample-contract.md\tonly three fields\n' > "$tmp/fx/anchors.tsv"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect M5 2 "$got_rc" "contract_anchor_row_malformed" "$got_out"

# M6 short literal
make_fixture
printf 'short\tdocs/sample-contract.md\ttiny pin\tnote\n' > "$tmp/fx/anchors.tsv"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect M6 2 "$got_rc" "contract_anchor_literal_too_short" "$got_out"

# M7 duplicate id
make_fixture
printf '%s\t%s\t%s\t%s\n' "sample-discriminator" "docs/sample-contract.md" \
  "Unrelated surrounding prose that may change" "second row same id" >> "$tmp/fx/anchors.tsv"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect M7 2 "$got_rc" "contract_anchor_duplicate_id" "$got_out"

# M8 table missing
make_fixture
run "$tmp/fx" "$tmp/fx/missing.tsv"
expect M8 2 "$got_rc" "contract_anchor_table_missing" "$got_out"

# M9 malformed row + drifted anchor: both reported in one run, rc 2
make_fixture
printf 'bad-row\tdocs/sample-contract.md\tonly three fields\n' >> "$tmp/fx/anchors.tsv"
perl -pi -e 's/decided by exactly one discriminating predicate/decided informally/' "$tmp/fx/docs/sample-contract.md"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect M9 2 "$got_rc" "contract_anchor_table_invalid" "$got_out"
if [[ "$got_out" != *"contract_anchor_row_malformed"* || "$got_out" != *"contract_anchor_missing: sample-discriminator"* ]]; then
  note "FAIL M9-completeness: expected both the integrity error and the drift finding in one run"
  note "$got_out"
  fail=1
else
  note "ok M9-completeness"
fi

# B1 benign neighbor: same line, outside the pinned span
make_fixture
perl -pi -e 's/predicate here\./predicate here, with a clarifying tail./' "$tmp/fx/docs/sample-contract.md"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect B1 0 "$got_rc" "contract_anchor_gate_ok" "$got_out"

# B2 unrelated file edited
make_fixture
printf 'More free text.\n' >> "$tmp/fx/docs/other.md"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect B2 0 "$got_rc" "contract_anchor_gate_ok" "$got_out"

# B3 anchored file grows elsewhere
make_fixture
printf '\n## New unrelated section\n\nNew prose.\n' >> "$tmp/fx/docs/sample-contract.md"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect B3 0 "$got_rc" "contract_anchor_gate_ok" "$got_out"

# D1 differential attribution: two anchors, one broken
make_fixture
printf '%s\t%s\t%s\t%s\n' "healthy-anchor" "docs/sample-contract.md" \
  "Unrelated surrounding prose that may change freely." "healthy row" >> "$tmp/fx/anchors.tsv"
perl -pi -e 's/decided by exactly one discriminating predicate/decided informally/' "$tmp/fx/docs/sample-contract.md"
run "$tmp/fx" "$tmp/fx/anchors.tsv"
expect D1 1 "$got_rc" "contract_anchor_missing: sample-discriminator" "$got_out"
if [[ "$got_out" == *"healthy-anchor"* ]]; then
  note "FAIL D1-attribution: healthy anchor reported in failure output"
  fail=1
else
  note "ok D1-attribution"
fi

if [[ "$fail" -ne 0 ]]; then
  echo "test_check_contract_anchors: FAIL"
  exit 1
fi
echo "test_check_contract_anchors: ok"
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