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_controlled_escalation_pins.sh

View on GitHub
#!/usr/bin/env bash
# Self-contained RED-baseline for the controlled-escalation pin family (family 8
# in test_ai_coding_implementation_gates.sh). Review rounds ua4/ua5 (spec 031)
# found that prose claims of mutation evidence are unverifiable from a bounded
# review packet; this test makes the walk reproducible in CI and visible in the
# diff: for EVERY family-8 pin, an applied deletion mutation in a throwaway copy
# must red the fixture on that pin's own assertion (differential attribution —
# the fixture exits at first failure, so every earlier assertion passed under
# the mutant), with green unmutated controls before and after and a
# tree-isolation probe proving the harness read the mutated copy, not the live
# tree. The pin list is parsed from the fixture itself so a new pin cannot be
# added without automatically entering this walk.
set -euo pipefail
# The copy gets its own repository; inherited git variables (set inside git
# hooks, for one) would point git at the real one instead.
unset GIT_DIR GIT_WORK_TREE GIT_INDEX_FILE GIT_OBJECT_DIRECTORY \
  GIT_ALTERNATE_OBJECT_DIRECTORIES GIT_COMMON_DIR GIT_CEILING_DIRECTORIES \
  GIT_NAMESPACE

script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd -P)"
repo_root="$(cd "$script_dir/../../.." && pwd -P)"
fixture_rel="skills/skill-extraction-workflow/scripts/test_ai_coding_implementation_gates.sh"
ref_rel="skills/skill-extraction-workflow/references/source-to-skill-extraction.md"

fail() { printf 'FAIL: %s\n' "$1" >&2; exit 1; }

tmp_root="$(mktemp -d "${TMPDIR:-/tmp}/controlled-escalation-pins.XXXXXX")"
trap 'rm -rf "$tmp_root"' EXIT
# The fixture also reads the root contract and release docs. Preserve all
# input surfaces while deriving its root from the copied script location.
cp -R "$repo_root/skills" "$tmp_root/skills"
cp -R "$repo_root/agent-context" "$tmp_root/agent-context"
cp -R "$repo_root/docs" "$tmp_root/docs"
cp "$repo_root/AGENTS.md" "$tmp_root/AGENTS.md"
# The fixture's teardown sweep lists the repository's Markdown through git, so
# the copy needs an index; nothing is committed, which keeps user commit hooks
# and signing out of the run.
cp "$repo_root/.gitignore" "$tmp_root/.gitignore"
git -C "$tmp_root" init -q
git -C "$tmp_root" add -A
copy_fixture="$tmp_root/$fixture_rel"
copy_ref="$tmp_root/$ref_rel"
[[ -f "$copy_fixture" && -f "$copy_ref" ]] || fail "copy is missing the fixture or the reference"

# Parse family-8 pins out of the fixture: each call is
#   assert_in_section "$EXTRACTION_METHOD_REF" "$BLOCKED_VERIFICATION_SECTION" <quoted phrase> \
#     "<label>"
# The phrase may be single- or double-quoted (one pin contains an apostrophe).
pins_file="$tmp_root/pins.tsv"
python3 - "$repo_root/$fixture_rel" "$pins_file" <<'PY'
import re, sys
src, out = sys.argv[1], sys.argv[2]
text = open(src).read()
pattern = re.compile(
    r'assert_in_section "\$EXTRACTION_METHOD_REF" "\$BLOCKED_VERIFICATION_SECTION" '
    r"(?:'([^']+)'|\"([^\"]+)\") \\\n\s+\"([^\"]+)\"",
)
rows = []
for m in pattern.finditer(text):
    phrase = m.group(1) or m.group(2)
    rows.append((phrase, m.group(3)))
if len(rows) < 14:
    sys.exit(f"parsed only {len(rows)} family-8 pins; parser or fixture drifted")
with open(out, "w") as f:
    for phrase, label in rows:
        f.write(f"{phrase}\t{label}\n")
print(len(rows))
PY
pin_count="$(wc -l < "$pins_file" | tr -d ' ')"
# Parser-completeness check (round ua21 P2): the regex must account for EVERY
# family-8 assertion in the fixture — a call whose syntax the regex does not
# recognize would silently drop out of the walk. The raw call count is the
# oracle the parse must match.
raw_count="$(grep -c 'assert_in_section "\$EXTRACTION_METHOD_REF" "\$BLOCKED_VERIFICATION_SECTION"' "$repo_root/$fixture_rel")"
[[ "$pin_count" == "$raw_count" ]] || fail "parser dropped family-8 assertions: parsed $pin_count of $raw_count calls"

run_copy() { TMPDIR="$tmp_root" bash "$copy_fixture" 2>&1; }

# Control: the unmutated copy is green, proving the harness reads the copy.
control_out="$(run_copy)" || fail "pre-control not green: $control_out"

pristine="$tmp_root/ref.pristine"
cp "$copy_ref" "$pristine"

while IFS=$'\t' read -r phrase label; do
  count="$(python3 - "$pristine" "$phrase" <<'PY'
import sys
print(open(sys.argv[1]).read().count(sys.argv[2]))
PY
)"
  [[ "$count" == "1" ]] || fail "pin phrase not unique in reference ($count hits): $phrase"
  python3 - "$pristine" "$copy_ref" "$phrase" <<'PY'
import sys
src, dst, phrase = sys.argv[1], sys.argv[2], sys.argv[3]
open(dst, "w").write(open(src).read().replace(phrase, "", 1))
PY
  if out="$(run_copy)"; then
    fail "mutant stayed green (deleted: $phrase)"
  fi
  last="$(printf '%s\n' "$out" | tail -1)"
  case "$last" in
    *"$label"*) : ;;
    *) fail "mutant red on the wrong assertion — expected [$label], got: $last" ;;
  esac
  cp "$pristine" "$copy_ref"
done < "$pins_file"

# Relocation probe (round ua8 P2): a deletion mutant cannot distinguish a
# section-bound helper from a whole-file grep. Move the lead phrase OUT of the
# Blocked Verification section to a decoy heading at the end of the file: a
# whole-file search would stay green, a section-bound one must red on the
# owning assertion.
python3 - "$pristine" "$copy_ref" <<'PY'
import sys
src, dst = sys.argv[1], sys.argv[2]
phrase = "Sandbox-denial triage precedes any escalation"
text = open(src).read()
assert text.count(phrase) == 1
open(dst, "w").write(text.replace(phrase, "", 1) + "\n## Relocation decoy\n\n" + phrase + "\n")
PY
if out="$(run_copy)"; then
  fail "relocation probe: section-bound assertion stayed green with the phrase outside its section"
fi
case "$(printf '%s\n' "$out" | tail -1)" in
  *"controlled escalation (invariant: triage before escalation"*) : ;;
  *) fail "relocation probe: red on the wrong assertion: $(printf '%s\n' "$out" | tail -1)" ;;
esac
cp "$pristine" "$copy_ref"

# Reachability probe (round ua15 P2): family 8 also carries an
# assert_same_bullet pin routing the entrypoint to the owning section; that pin
# is not an assert_in_section call, so it gets its own applied mutation here —
# strip the section anchor from the entrypoint bullet and require the fixture
# to red on the reachability assertion.
copy_skill="$tmp_root/skills/skill-extraction-workflow/SKILL.md"
skill_pristine="$tmp_root/skill.pristine"
cp "$copy_skill" "$skill_pristine"
python3 - "$skill_pristine" "$copy_skill" <<'PY'
import sys
src, dst = sys.argv[1], sys.argv[2]
anchor = "references/source-to-skill-extraction.md#blocked-verification-and-source-read-remediation"
text = open(src).read()
if anchor not in text:
    sys.exit("entrypoint anchor not found; reachability probe cannot run")
open(dst, "w").write(text.replace(anchor, "references/source-to-skill-extraction.md", 1))
PY
if out="$(run_copy)"; then
  fail "reachability probe: fixture stayed green with the entrypoint route removed"
fi
case "$(printf '%s\n' "$out" | tail -1)" in
  *"reachability: entrypoint routes to the Blocked Verification section"*) : ;;
  *) fail "reachability probe: red on the wrong assertion: $(printf '%s\n' "$out" | tail -1)" ;;
esac
cp "$skill_pristine" "$copy_skill"

# Post-control green, and tree isolation: a mutated copy reds while the live
# tree's own fixture stays green.
run_copy >/dev/null || fail "post-control not green"
python3 - "$pristine" "$copy_ref" <<'PY'
import sys
src, dst = sys.argv[1], sys.argv[2]
open(dst, "w").write(open(src).read().replace("Sandbox-denial triage precedes any escalation", "", 1))
PY
if run_copy >/dev/null; then fail "tree-isolation probe: mutated copy stayed green"; fi
bash "$repo_root/$fixture_rel" >/dev/null || fail "tree-isolation probe: live tree fixture not green"
cp "$pristine" "$copy_ref"

echo "test_controlled_escalation_pins: ok ($pin_count applied mutations, each red on its owning assertion; controls green)"
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