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_frozen_case_sanctity.sh

View on GitHub
#!/usr/bin/env bash
# Frozen-case sanctity gate (regressions-are-sacred, deterministic half).
#
# SCOPE — read this before citing the lane as evidence. A frozen eval case
# (routing task-bank row, golden trace) is a pinned judgment: deleting it or
# rewriting its judgment fields makes a red disappear without anyone ruling on
# it. This lane makes that trade VISIBLE: any base-relative deletion or
# judgment-field change of a frozen case must be named by an ADDED
# source-register line carrying `case-retired: <id>` or `case-rescoped: <id>`.
# It does NOT judge whether the retirement/rescope is justified — that ruling
# belongs to the round's independent review (the register row is what puts it
# in front of the reviewer). Like the impact-chain gate, it trusts the author
# to write the declaration; it defends against SILENT trades, not forged ones.
# Without CCL_SKILL_BASE_REF (or an unresolvable base) it degrades to an
# explicit skip token — a skipped run is not a passed run.
set -u

ROOT="${SANCTITY_ROOT:-$(cd "$(dirname "$0")/../../.." && pwd)}"
[ -n "${SANCTITY_ROOT:-}" ] && echo "NOTICE: SANCTITY_ROOT set — testing tree: $ROOT" >&2
REGISTER="skills/skill-extraction-workflow/references/source-register.md"
BANK="eval/routing-tasks.jsonl"
TRACES_DIR="eval/golden-traces"

BASE="${CCL_SKILL_BASE_REF:-}"
if [ -z "$BASE" ]; then
  echo "frozen_case_sanctity_skipped no-base-ref (set CCL_SKILL_BASE_REF to enable; skipped is not passed)"
  exit 0
fi
if ! git -C "$ROOT" rev-parse --verify --quiet "${BASE}^{commit}" >/dev/null; then
  echo "frozen_case_sanctity_skipped base-unresolvable ($BASE; skipped is not passed)"
  exit 0
fi

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

# Base snapshots; a path absent at base means every current case is new (no
# violation possible on that surface).
git -C "$ROOT" show "$BASE:$BANK" > "$TMPDIR_SANCTITY/base-bank.jsonl" 2>/dev/null || : > "$TMPDIR_SANCTITY/base-bank.jsonl"
git -C "$ROOT" show "$BASE:$REGISTER" > "$TMPDIR_SANCTITY/base-register.md" 2>/dev/null || : > "$TMPDIR_SANCTITY/base-register.md"
mkdir -p "$TMPDIR_SANCTITY/base-traces"
# -r: enumerate blobs recursively so a trace in a subdirectory is still guarded
# (the head-side walk below recurses symmetrically).
n=0
git -C "$ROOT" ls-tree -r --name-only "$BASE" -- "$TRACES_DIR/" 2>/dev/null | while IFS= read -r tp; do
  case "$tp" in
    *.json)
      n=$((n+1))
      git -C "$ROOT" show "$BASE:$tp" > "$TMPDIR_SANCTITY/base-traces/trace-$n-$(basename "$tp")" 2>/dev/null || true ;;
  esac
done

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

root, tmp, register_rel, bank_rel, traces_rel = sys.argv[1:6]
fail = 0

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

def load_bank(path):
    rows = {}
    if not os.path.exists(path):
        return rows
    with open(path, encoding="utf-8") as fh:
        for raw in fh:
            raw = raw.strip()
            if not raw:
                continue
            try:
                row = json.loads(raw)
            except json.JSONDecodeError:
                continue  # malformed rows are the integrity lane's finding, not ours
            rid = row.get("id")
            if rid:
                rows[rid] = row
    return rows

def judgment(row):
    # The judgment surface of a bank case: what outcome passes or fails it.
    # Provenance/commentary fields (source, why_expected, frozen_at_sha) may
    # change without re-scoping the case.
    return (
        row.get("expected_skill"),
        sorted(row.get("acceptable") or []) if isinstance(row.get("acceptable"), list) else row.get("acceptable"),
        sorted(row.get("must_not_route_to") or []) if isinstance(row.get("must_not_route_to"), list) else row.get("must_not_route_to"),
    )

base_bank = load_bank(os.path.join(tmp, "base-bank.jsonl"))
head_bank = load_bank(os.path.join(root, bank_rel))

violations = []  # (kind, id)
for rid, row in base_bank.items():
    if rid not in head_bank:
        violations.append(("deleted bank case", rid))
    elif judgment(row) != judgment(head_bank[rid]):
        violations.append(("re-scoped bank case (judgment fields changed)", rid))

def load_trace(path):
    try:
        with open(path, encoding="utf-8") as fh:
            return json.load(fh)
    except (OSError, json.JSONDecodeError):
        return None

base_traces = {}
base_dir = os.path.join(tmp, "base-traces")
for name in sorted(os.listdir(base_dir)):
    data = load_trace(os.path.join(base_dir, name))
    if isinstance(data, dict) and data.get("id"):
        base_traces[data["id"]] = data

head_traces = {}
head_dir = os.path.join(root, traces_rel)
if os.path.isdir(head_dir):
    for dirpath, _dirnames, filenames in os.walk(head_dir):
        for name in sorted(filenames):
            if not name.endswith(".json"):
                continue
            data = load_trace(os.path.join(dirpath, name))
            if isinstance(data, dict) and data.get("id"):
                head_traces[data["id"]] = data

for tid, data in base_traces.items():
    if tid not in head_traces:
        violations.append(("deleted golden trace", tid))
    elif data.get("assert") != head_traces[tid].get("assert"):
        violations.append(("re-scoped golden trace (assert block changed)", tid))

# Added register lines = head lines not present at base (the register is
# append-only, so a set diff is the added-row surface). Only added Markdown
# TABLE ROWS may carry adjudication credit — an adjudication is a register row
# a reviewer rules on, so an HTML comment or loose prose that merely mentions
# the token mints nothing.
with open(os.path.join(tmp, "base-register.md"), encoding="utf-8") as fh:
    base_lines = set(fh.read().splitlines())
register_path = os.path.join(root, register_rel)
added_rows = []
if os.path.exists(register_path):
    with open(register_path, encoding="utf-8") as fh:
        added_rows = [
            ln for ln in fh.read().splitlines()
            if ln not in base_lines and ln.lstrip().startswith("|")
        ]
added_blob = "\n".join(added_rows)

import re
def adjudicated(case_id):
    # Token-bounded: `case-retired: foo` must not be credited by
    # `case-retired: foobar` (ids use [A-Za-z0-9_-]).
    pattern = re.compile(
        r"case-(?:retired|rescoped):\s*" + re.escape(case_id) + r"(?![A-Za-z0-9_-])"
    )
    return bool(pattern.search(added_blob))

for kind, cid in violations:
    if adjudicated(cid):
        continue
    bad(
        f"{kind} '{cid}' with no adjudication row — a frozen case may not be "
        f"silently traded away; add a source-register row this round containing "
        f"`case-retired: {cid}` or `case-rescoped: {cid}` (with the why), so the "
        f"independent review rules on it"
    )

if fail:
    sys.exit(1)
print(f"frozen_case_sanctity_ok bank_base={len(base_bank)} traces_base={len(base_traces)} violations=0")
PY
status=$?
if [ $status -ne 0 ]; then
  echo "frozen_case_sanctity_failed" >&2
  exit 1
fi
exit 0
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