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_entrypoint_form_census.sh

View on GitHub
#!/usr/bin/env bash
# Regression for the entrypoint form census. The census is an instrument whose
# only value is that a later round recomputes the same quantity, so the cases
# below pin the definitions the script documents -- what counts as one rule,
# what counts as a prohibition, and what counts as a named baseline failure --
# rather than the figures of any particular entrypoint, which move every round.
set -uo pipefail

DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd -P)"
CENSUS="$DIR/entrypoint_form_census.py"
WORK="$(mktemp -d "${TMPDIR:-/tmp}/entrypoint-form-census.XXXXXX")"
trap 'rm -rf "$WORK"' EXIT

fails=0
check() { if eval "$2"; then echo "ok   - $1"; else echo "FAIL - $1"; fails=$((fails+1)); fi; }

[ -f "$CENSUS" ] || { echo "FAIL: census missing: $CENSUS" >&2; exit 1; }

field() { printf '%s\n' "$1" | sed -n "s/^$2=//p"; }

# One rule per top-level bullet: the sub-bullet and the continuation line belong
# to the rule above them, and the blank line between them does not close it.
# Getting this wrong inflates every per-rule figure the census reports.
# The prohibitions are placed in the continuation and the sub-bullet, never in
# the bullet's own first line: a rule COUNT cannot detect a parser that drops
# continuations, because a dropped continuation is still not a new top-level
# bullet. The token total is the quantity that moves when the defect is present,
# so that is what the case asserts.
cat >"$WORK/one-rule.md" <<'MD'
# Entry

## Core Rules

### A group

- A rule head with no imperative of its own.

  A continuation line that must hold.

  - A sub-bullet that must also hold.

## After

- A bullet outside Core Rules that must not be counted.
MD
out="$(python3 "$CENSUS" "$WORK/one-rule.md")"; rc=$?
check "sub-bullets and continuations separated by blank lines stay inside one rule" \
  '[ "$rc" = 0 ] && [ "$(field "$out" rules)" = 1 ] && [ "$(field "$out" prohibitive_tokens)" = 2 ]'
# This case owns the section boundary alone: a parser that ran past `## After`
# would report two rules, so the rule count is the quantity that moves here.
check "the census stops at the next same-level heading" \
  '[ "$(field "$out" rules)" = 1 ]'

# A prohibition with no named baseline failure is the diagnostic set; the same
# rule with its failure named must leave that set. The pair is the control: if
# the failure-shape vocabulary stopped matching, the first case would still pass
# and only the second would fail, which is what makes the pair informative.
cat >"$WORK/unanchored.md" <<'MD'
# Entry

## Core Rules

### A group

- A rule that must never be skipped.
MD
out="$(python3 "$CENSUS" "$WORK/unanchored.md")"
check "a prohibition with no named baseline failure is reported unanchored" \
  '[ "$(field "$out" unanchored_prohibition_rules)" = 1 ] && [ "$(field "$out" rules_naming_baseline_failure)" = 0 ]'

cat >"$WORK/anchored.md" <<'MD'
# Entry

## Core Rules

### A group

- A rule that must never be skipped. Failure shape: the step is skipped under time pressure.
MD
out="$(python3 "$CENSUS" "$WORK/anchored.md")"
check "the same prohibition with its baseline failure named leaves the unanchored set" \
  '[ "$(field "$out" unanchored_prohibition_rules)" = 0 ] && [ "$(field "$out" rules_naming_baseline_failure)" = 1 ]'

# A rule with no prohibitive token is not in the diagnostic set whether or not it
# names a failure: the set is prohibitions the form table has something to say
# about, not every rule that omits a rationale.
cat >"$WORK/no-prohibition.md" <<'MD'
# Entry

## Core Rules

### A group

- State the artifact's parts, in order.
MD
out="$(python3 "$CENSUS" "$WORK/no-prohibition.md")"
check "a rule carrying no prohibitive token is outside the diagnostic set" \
  '[ "$(field "$out" prohibitive_tokens)" = 0 ] && [ "$(field "$out" unanchored_prohibition_rules)" = 0 ]'

# The capitalised spellings are emphasis in this package and are counted; a word
# that merely contains one of them is not a token.
cat >"$WORK/tokens.md" <<'MD'
# Entry

## Core Rules

### A group

- This MUST hold and NEVER lapses, and the mustard and nevertheless here are not tokens.
MD
out="$(python3 "$CENSUS" "$WORK/tokens.md")"
check "capitalised emphasis counts as prohibitive and a word merely containing one does not" \
  '[ "$(field "$out" prohibitive_tokens)" = 2 ]'

# The alternation is leftmost and non-overlapping, so a phrase absorbs the words
# inside it. Two independent review lenses read the previous comment as promising
# the opposite, which is exactly the failure this case now pins: the documented
# counting rule and the reported figure have to be the same ruler.
cat >"$WORK/overlap.md" <<'MD'
# Entry

## Core Rules

### A group

- This must not be counted twice, and this cannot be either.
MD
out="$(python3 "$CENSUS" "$WORK/overlap.md")"
check "a phrase absorbs the word inside it: 'must not' is one token, not two" \
  '[ "$(field "$out" prohibitive_tokens)" = 2 ]'

# An existing but empty Core Rules section is an error, not a zero-rule census:
# a section that lost its rules must not report as a clean sheet either.
cat >"$WORK/empty-core.md" <<'MD'
# Entry

## Core Rules

### A group

Prose with no top-level bullet.

## After

- A bullet outside Core Rules.
MD
out="$(python3 "$CENSUS" "$WORK/empty-core.md" 2>&1)"; rc=$?
check "an existing but empty Core Rules section is an error, never a zero-rule census" \
  '[ "$rc" != 0 ] && case "$out" in *entrypoint_form_census_error*) true;; *) false;; esac'

# An entrypoint with no Core Rules section is an error, not a zero: reporting
# zero rules would let a renamed or moved section read as a clean sheet.
cat >"$WORK/no-core.md" <<'MD'
# Entry

## Something Else

- A bullet.
MD
out="$(python3 "$CENSUS" "$WORK/no-core.md" 2>&1)"; rc=$?
check "a file with no Core Rules heading is an error, never an empty census" \
  '[ "$rc" != 0 ] && case "$out" in *entrypoint_form_census_error*) true;; *) false;; esac'

# The shipped entrypoint must parse, or the instrument silently stops measuring
# the only file it exists for.
out="$(python3 "$CENSUS" "$DIR/../SKILL.md")"; rc=$?
check "the shipped entrypoint parses and reports a non-zero rule count" \
  '[ "$rc" = 0 ] && [ "$(field "$out" rules)" -gt 0 ] && case "$out" in *entrypoint_form_census_ok*) true;; *) false;; esac'

if [ "$fails" -ne 0 ]; then
  echo "test_entrypoint_form_census: $fails failing case(s)"
  exit 1
fi
echo "test_entrypoint_form_census: 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