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_eval_routing_bank_surface_binding.sh

View on GitHub
#!/usr/bin/env bash
# Regression test for eval-routing-bank's routing_surface self-identification:
# every emitted report must name the exact surface it graded — the raw
# description-line surface (byte-compatible with the binding wrapper's
# surface_hash), a per-skill description-line hash map, the graded catalog
# text's own hash (post desc-budget truncation), and the bank bytes — so a
# round artifact can never be attributed to the wrong wording by operator
# assertion alone. Uses a fake claude earlier in PATH; never invokes a real
# Claude CLI or account. Grading semantics must be untouched.
set -euo pipefail
# Ruby takes its encoding from the locale; under a POSIX/unset locale it reads the UTF-8 skill text as US-ASCII and crashes. Pin UTF-8, as CI runs.
case " ${RUBYOPT:-} " in *" -Ku "*) ;; *) export RUBYOPT="-Ku${RUBYOPT:+ $RUBYOPT}" ;; esac

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
EVAL_SCRIPT="$SCRIPT_DIR/eval-routing-bank.rb"
[ -f "$EVAL_SCRIPT" ] || { echo "FAIL: eval script not found: $EVAL_SCRIPT" >&2; exit 1; }

TMP="$(mktemp -d "${TMPDIR:-/tmp}/eval-routing-bank-surface.XXXXXX")"
cleanup() { rm -rf "$TMP"; }
trap cleanup EXIT

fail() { echo "FAIL: $*" >&2; exit 1; }

REPO="$TMP/repo"
FAKE_BIN="$TMP/bin"
mkdir -p "$REPO/skills/testing-strategy" "$REPO/skills/product-rd-workflow" "$REPO/eval" "$FAKE_BIN"

git -C "$TMP" init -q repo
git -C "$REPO" config user.email test@example.invalid
git -C "$REPO" config user.name "Test User"

cat > "$REPO/skills/testing-strategy/SKILL.md" <<'EOF'
---
description: Use when choosing test layers and regression evidence.
---
# Testing Strategy
EOF

cat > "$REPO/skills/product-rd-workflow/SKILL.md" <<'EOF'
---
description: Use as the product delivery entry router for features and specs.
---
# Product RD Workflow
EOF

cat > "$REPO/eval/routing-tasks.jsonl" <<'EOF'
{"id":"surface-case","utterance":"补一个回归测试","expected_skill":"testing-strategy","frozen_at_sha":""}
EOF

git -C "$REPO" add -A
git -C "$REPO" commit -qm "fixture"

cat > "$FAKE_BIN/claude" <<'EOF'
#!/usr/bin/env bash
cat >/dev/null
printf '{"selected_skill": "testing-strategy", "confidence": 0.9, "rationale_short": "stub"}\n'
EOF
chmod +x "$FAKE_BIN/claude"

report1="$TMP/report1.json"
report2="$TMP/report2.json"
set +e
out1="$(PATH="$FAKE_BIN:$PATH" ruby "$EVAL_SCRIPT" "$REPO" --json "$report1" --timeout 60 2>&1)"
rc1=$?
out2="$(PATH="$FAKE_BIN:$PATH" ruby "$EVAL_SCRIPT" "$REPO" --json "$report2" --timeout 60 --desc-budget-chars 10 2>&1)"
rc2=$?
set -e
[ "$rc1" = "0" ] || fail "plain arm exited $rc1: $out1"
[ "$rc2" = "0" ] || fail "budget arm exited $rc2: $out2"

REPO_DIR="$REPO" python3 - "$report1" "$report2" <<'PYEOF'
import hashlib, json, os, sys, glob

report1 = json.load(open(sys.argv[1]))
report2 = json.load(open(sys.argv[2]))
repo = os.environ["REPO_DIR"]

def fail(msg):
    print("FAIL: " + msg, file=sys.stderr)
    sys.exit(1)

rs1 = report1.get("routing_surface")
if not isinstance(rs1, dict):
    fail("report has no routing_surface object")

# Grading semantics untouched: the stub grader's verdict still lands as PASS.
if report1["results"][0]["status"] != "PASS":
    fail("grading changed: expected PASS, got %r" % report1["results"][0]["status"])

bank_bytes = open(os.path.join(repo, "eval", "routing-tasks.jsonl"), "rb").read()
if rs1.get("bank_sha256") != hashlib.sha256(bank_bytes).hexdigest():
    fail("bank_sha256 does not match the bank file bytes")

# Recompute the wrapper-compatible surface: dir-name-tagged raw description
# lines in sorted glob order (line bytes include the trailing newline, matching
# `grep -m1 '^description:'` piped output), then the bank bytes.
surface = b""
expected_per_skill = {}
for path in sorted(glob.glob(os.path.join(repo, "skills", "*", "SKILL.md"))):
    name = os.path.basename(os.path.dirname(path))
    line = None
    with open(path, "rb") as f:
        for l in f:
            if l.startswith(b"description:"):
                line = l
                break
    if line is None:
        continue
    surface += name.encode() + b"\t" + line
    expected_per_skill[name] = hashlib.sha256(line).hexdigest()
if rs1.get("descriptions_sha256") != hashlib.sha256(surface + bank_bytes).hexdigest():
    fail("descriptions_sha256 does not match the wrapper-compatible surface bytes")

per_skill = rs1.get("per_skill_description_line_sha256")
if per_skill != expected_per_skill:
    fail("per_skill_description_line_sha256 mismatch: got %r expected %r" % (per_skill, expected_per_skill))

if not rs1.get("catalog_sha256"):
    fail("catalog_sha256 missing or empty")

rs2 = report2.get("routing_surface")
if not isinstance(rs2, dict):
    fail("budget-arm report has no routing_surface object")
if rs2.get("catalog_sha256") == rs1.get("catalog_sha256"):
    fail("desc-budget truncation must change catalog_sha256")
if rs2.get("descriptions_sha256") != rs1.get("descriptions_sha256"):
    fail("desc-budget truncation must NOT change the raw descriptions_sha256")
print("surface binding assertions ok")
PYEOF

# The multiline-description differential (both review lanes' finding): editing a
# `description: >-` CONTINUATION line changes what the grader sees but not the
# raw first line, so descriptions_sha256 must stay UNCHANGED (the documented
# raw-surface blind spot) while catalog_sha256 must CHANGE — which is exactly
# why the graded-catalog binding is load-bearing on its own and the round
# wrapper cross-checks it independently.
mkdir -p "$REPO/skills/platform-observability"
cat > "$REPO/skills/platform-observability/SKILL.md" <<'EOF'
---
description: >-
  Use when wiring service logs and metrics.
  Continuation line one for the multiline fixture.
---
# Platform Observability
EOF

report3="$TMP/report3.json"
report4="$TMP/report4.json"
set +e
out3="$(PATH="$FAKE_BIN:$PATH" ruby "$EVAL_SCRIPT" "$REPO" --json "$report3" --timeout 60 2>&1)"
rc3=$?
set -e
[ "$rc3" = "0" ] || fail "multiline baseline arm exited $rc3: $out3"

perl -pi -e 's/Continuation line one for the multiline fixture\./Continuation line one, materially reworded\./' "$REPO/skills/platform-observability/SKILL.md"

set +e
out4="$(PATH="$FAKE_BIN:$PATH" ruby "$EVAL_SCRIPT" "$REPO" --json "$report4" --timeout 60 2>&1)"
rc4=$?
set -e
[ "$rc4" = "0" ] || fail "multiline mutated arm exited $rc4: $out4"

python3 - "$report3" "$report4" <<'PYEOF'
import json, sys

r3 = json.load(open(sys.argv[1]))["routing_surface"]
r4 = json.load(open(sys.argv[2]))["routing_surface"]

def fail(msg):
    print("FAIL: " + msg, file=sys.stderr)
    sys.exit(1)

if r3["descriptions_sha256"] != r4["descriptions_sha256"]:
    fail("editing a continuation line must NOT change the raw descriptions_sha256 (that blind spot is documented, not fixed here)")
if r3["catalog_sha256"] == r4["catalog_sha256"]:
    fail("editing a continuation line MUST change catalog_sha256 — the graded-catalog binding is load-bearing")
print("multiline differential assertions ok")
PYEOF

echo "test_eval_routing_bank_surface_binding: 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