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/generic-r0-leak-scan.sh

View on GitHub
#!/usr/bin/env bash
# generic-r0-leak-scan.sh — deterministic PUBLIC fallback for the R0 leakage gate.
#
# When the maintainer's private ALIAS_AUDIT_CMD is unavailable (a normal local
# machine), check-ccl-skills.sh runs this scan instead of leaving only an
# "audit skipped" notice. It is a HIGH-SIGNAL, LOW-FALSE-POSITIVE public check —
# NOT a replacement for the private alias audit.
#
# Scope: ONLY the ADDED lines of the current git diff (committed base..HEAD,
# staged, unstaged, and untracked) restricted to shared-skill MARKDOWN surfaces
# (skills/**/*.md, README.md, docs/**/*.md,
# packages/opencode-plugin/commands/**/*.md,
# .opencode/commands/**/*.md). Diff-scoping is deliberate: it never re-polices
# pre-existing known debt, only what THIS change introduces. Markdown-only is
# deliberate too: scripts and YAML overlays legitimately contain example tokens
# and path-handling code, and the private alias audit (not this fallback) is the
# comprehensive gate of record over every file type.
#
# Detected leak classes (each requires a CONCRETE shape, so prose and angle
# placeholders like </Users> or <repo> do not trip it):
#   - absolute local paths: /Users/<seg>, /home/<seg>, /private/var/<seg>, C:\<seg>
#   - RFC1918 private IPv4 literals (10/8, 172.16-31/12, 192.168/16) — NOT loopback
#   - internal-only hostnames: <label>.internal / .intranet / .corp
#   - secret/token literals: key=<12+char quoted value>, or known vendor token prefixes
#
# Exit codes: clean=0 (prints generic_r0_leak_scan_ok), leak found=1 (prints the
# offending lines), degraded=0 (prints generic_r0_leak_scan_degraded — a DISTINCT
# status, NOT a reassuring _ok). Degraded fires when coverage is incomplete: not a
# git work tree, OR no diff base resolves (no CCL_SKILL_BASE_REF / @{upstream} /
# origin/main merge-base) while HEAD exists, so committed branch commits were NOT
# scanned — the exact shallow / detached-HEAD CI case where a leak already committed
# on the branch would otherwise pass as a silent _ok. Degraded is WARNING-PASS
# (exit 0) by default because this is a best-effort preflight and the private
# ALIAS_AUDIT_CMD is the gate of record; opt IN to a hard failure with
# CCL_SKILL_R0_STRICT_BASE=1. A leak found in whatever WAS scanned still blocks
# (exit 1) regardless of degraded. `--self-test` validates the matcher and the
# clean/degraded status decision against in-memory fixtures (no git) and exits 0/1.
set -euo pipefail

# High-signal leak patterns (rg / Rust-regex syntax). A match anywhere on an
# added line flags it. Kept narrow to hold false positives down.
leak_patterns=(
  '/Users/[A-Za-z0-9._-]'
  '/home/[A-Za-z0-9._-]'
  '/private/var/[A-Za-z0-9._-]'
  '[A-Za-z]:\\[A-Za-z0-9._-]'
  '(?:^|[^0-9.])10\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}(?:[^0-9]|$)'
  '(?:^|[^0-9.])192\.168\.[0-9]{1,3}\.[0-9]{1,3}(?:[^0-9]|$)'
  '(?:^|[^0-9.])172\.(?:1[6-9]|2[0-9]|3[01])\.[0-9]{1,3}\.[0-9]{1,3}(?:[^0-9]|$)'
  '[A-Za-z0-9][A-Za-z0-9-]*\.(?:internal|intranet|corp)(?:[^A-Za-z0-9]|$)'
  '(?:^|[^A-Za-z0-9])AKIA[0-9A-Z]{16}(?:[^0-9A-Z]|$)'
  '(?:^|[^A-Za-z0-9])gh[opsu]_[A-Za-z0-9]{36}'
  '(?:^|[^A-Za-z0-9])glpat-[A-Za-z0-9_-]{20}'
  '(?:^|[^A-Za-z0-9])xox[baprs]-[A-Za-z0-9-]{10,}'
  '(?:^|[^A-Za-z0-9])sk-[A-Za-z0-9]{20,}'
  '-----BEGIN [A-Z ]*PRIVATE KEY-----'
)
# Secret-assignment pattern carries both quote chars, so build it with double
# quotes (\" -> "), keeping rg escapes (\\s -> \s) intact.
leak_patterns+=( "(?i:api[_-]?key|secret(?:[_-]?key)?|access[_-]?key|client[_-]?secret|password|passwd|token|bearer)[\"']?\\s*[:=]\\s*[\"'][A-Za-z0-9_+/.=-]{12,}[\"']" )

# scan_stream: reads "path:lineno:content" lines on stdin, prints offenders on
# stdout. Returns 0 normally (offenders may be empty), 2 on rg error.
scan_stream() {
  local args=() p out rc=0
  for p in "${leak_patterns[@]}"; do args+=( -e "$p" ); done
  # Capture rg's real status in the else branch (a false `if` with no else would
  # otherwise reset $? to 0). rg: 0=match, 1=no match, 2=error.
  if out="$(rg --no-line-number --no-filename --color never "${args[@]}" 2>/dev/null)"; then
    rc=0
  else
    rc=$?
  fi
  if [ "$rc" -eq 0 ]; then
    printf '%s\n' "$out"
    return 0
  fi
  [ "$rc" -eq 1 ] && return 0   # no matches
  echo "generic_r0_leak_scan_error: rg exited $rc" >&2
  return 2
}

# emit_clean_result <degraded> <line_count> <file_count>
# Prints the clean-outcome status line and returns its exit code. Isolated from
# git so --self-test can exercise it. degraded=1 -> a DISTINCT scan_degraded
# status (base unavailable; committed branch commits NOT covered), WARNING-PASS
# (exit 0) by default, or BLOCK (exit 1) under CCL_SKILL_R0_STRICT_BASE=1.
emit_clean_result() {
  local degraded="$1" line_count="$2" file_count="$3"
  if [ "$degraded" = 1 ]; then
    echo "generic_r0_leak_scan_degraded: base unavailable (no CCL_SKILL_BASE_REF / @{upstream} / origin/main merge-base); committed branch commits NOT scanned — only worktree/staged/untracked. Best-effort preflight; degraded-clean is NOT proof, the private ALIAS_AUDIT_CMD is the gate of record. Set CCL_SKILL_BASE_REF for full coverage." >&2
    if [ "${CCL_SKILL_R0_STRICT_BASE:-0}" = 1 ]; then
      echo "generic_r0_leak_scan_degraded_blocking: CCL_SKILL_R0_STRICT_BASE=1 -> treating degraded coverage as a failure" >&2
      return 1
    fi
    return 0
  fi
  echo "generic_r0_leak_scan_ok: scanned ${line_count} added markdown line(s) across ${file_count} file(s); no high-signal public leak patterns"
  return 0
}

run_self_test() {
  # Fixtures: "<expect>\t<content>" where expect is flag|clean.
  local fixture_label='api_key'
  local fixture_value='abcdef0123456789xyz'
  local fixtures=(
    $'flag\t/Users/alice/secret/path here'
    $'flag\tconfig at /home/bob/.config/app'
    $'flag\t/private/var/folders/ab/private-thing'
    $'flag\twindows path C:\\Users\\admin\\file.txt'
    $'flag\tconnect to 10.'$'1.2.3 today'
    $'flag\tinternal host 192.'$'168.0.5 only'
    $'flag\treach 172.'$'20.1.1 over vpn'
    $'flag\tservice db.'$'internal is up'
    $'flag\tAWS key AKIA'$'ABCDEFGHIJKLMNOP rotated'
    $'flag\tgithub ghp_'$'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 leaked'
    "flag"$'\t'"$fixture_label = \"$fixture_value\" set"
    $'flag\tpassword: "hunter2hunter2hunter2"'
    $'flag\tbegin block -----BEGIN RSA PRIVATE KEY-----'
    $'clean\tsee <repo>/skills/foo for details'
    $'clean\tpath under /home/<user>/config'
    $'clean\tlocalhost 127.0.0.1 loopback only'
    $'clean\trelease version 1.2.3.4beta notes'
    $'clean\tset your api token in the settings page'
    $'clean\tthe secret sauce of good design'
    $'clean\tRFC1918 ranges like 10.x and 192.168.x'
    $'clean\tuse base64 to encode the payload'
    $'clean\ttask-runner sk module loaded'
    $'clean\texample.invalid is a reserved test host'
    $'clean\tSHA-256 digest of the file'
  )
  local failed=0 expect content line flagged
  local i=1
  for fx in "${fixtures[@]}"; do
    expect="${fx%%$'\t'*}"
    content="${fx#*$'\t'}"
    line="selftest:${i}:${content}"
    if [ -n "$(printf '%s\n' "$line" | scan_stream)" ]; then
      flagged=flag
    else
      flagged=clean
    fi
    if [ "$flagged" != "$expect" ]; then
      echo "generic_r0_leak_scan_self_test: MISMATCH expected=$expect got=$flagged :: $content" >&2
      failed=1
    fi
    i=$((i + 1))
  done
  # Status-decision unit: base-unavailable clean outcome must be a DISTINCT
  # scan_degraded (not a reassuring _ok), warning-pass by default, blocking under
  # strict; a covered clean outcome must be scan_ok.
  local dtext drc
  dtext="$(emit_clean_result 1 0 0 2>&1)" && drc=0 || drc=$?
  if ! printf '%s' "$dtext" | grep -q 'generic_r0_leak_scan_degraded'; then
    echo "generic_r0_leak_scan_self_test: emit_clean_result(degraded) must print scan_degraded" >&2; failed=1
  fi
  if [ "$drc" -ne 0 ]; then
    echo "generic_r0_leak_scan_self_test: degraded must be WARNING-PASS (exit 0) by default" >&2; failed=1
  fi
  dtext="$(CCL_SKILL_R0_STRICT_BASE=1 emit_clean_result 1 0 0 2>&1)" && drc=0 || drc=$?
  if [ "$drc" -eq 0 ]; then
    echo "generic_r0_leak_scan_self_test: CCL_SKILL_R0_STRICT_BASE=1 must make degraded BLOCK" >&2; failed=1
  fi
  if ! printf '%s' "$(emit_clean_result 0 5 2 2>&1)" | grep -q 'generic_r0_leak_scan_ok'; then
    echo "generic_r0_leak_scan_self_test: emit_clean_result(covered) must print scan_ok" >&2; failed=1
  fi

  if [ "$failed" -ne 0 ]; then
    echo "generic_r0_leak_scan_self_test_failed" >&2
    return 1
  fi
  echo "generic_r0_leak_scan_self_test_ok"
  return 0
}

# parse_diff: stdin = `git diff --unified=0` output; stdout = added markdown
# lines as "relpath:newlineno:content". Tracks the +++ target file and the new
# line counter from each @@ hunk header.
parse_diff() {
  awk '
    /^diff --git / { file=""; next }
    /^\+\+\+ / {
      f=$0; sub(/^\+\+\+ /,"",f)
      if (f=="/dev/null") { file=""; next }
      sub(/^b\//,"",f)
      file=f
      next
    }
    /^@@ / {
      if (match($0, /\+[0-9]+/)) { curline=substr($0, RSTART+1, RLENGTH-1)+0 }
      next
    }
    /^\+/ {
      if (file=="") next
      if (file !~ /\.md$/) next
      print file ":" curline ":" substr($0,2)
      curline++
      next
    }
  '
}

main_scan() {
  local root="${1:-.}"
  cd "$root"
  if ! git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
    echo "generic_r0_leak_scan_degraded: not a git work tree at '$root'; cannot diff added lines (non-blocking)"
    return 0
  fi

  local surfaces=( skills README.md docs packages/opencode-plugin/commands .opencode/commands )

  # Resolve diff base (mirrors check-ccl-skills.sh): explicit override, then
  # @{upstream}, then origin/main. merge_base may be empty when no base resolves
  # (shallow / detached-HEAD CI, no origin). The staged/unstaged/untracked scans
  # still run, but committed branch commits are then NOT covered — so when a HEAD
  # exists yet no base resolved, mark the clean outcome degraded rather than let a
  # branch-committed leak pass as a silent _ok.
  local base merge_base degraded=0
  base="${CCL_SKILL_BASE_REF:-}"
  if [ -z "$base" ]; then
    base="$(git rev-parse --abbrev-ref --symbolic-full-name '@{upstream}' 2>/dev/null || true)"
    [ -z "$base" ] && base="origin/main"
  fi
  merge_base="$(git merge-base "$base" HEAD 2>/dev/null || true)"
  if [ -z "$merge_base" ] && git rev-parse --verify -q HEAD >/dev/null 2>&1; then
    degraded=1
  fi

  local stream=""
  if [ -n "$merge_base" ]; then
    stream+="$(git diff --unified=0 "$merge_base" HEAD -- "${surfaces[@]}" 2>/dev/null | parse_diff)"$'\n'
  fi
  stream+="$(git diff --unified=0 --cached -- "${surfaces[@]}" 2>/dev/null | parse_diff)"$'\n'
  stream+="$(git diff --unified=0 -- "${surfaces[@]}" 2>/dev/null | parse_diff)"$'\n'

  # Untracked markdown files: every line counts as added.
  local f rel
  while IFS= read -r f; do
    [ -n "$f" ] || continue
    case "$f" in *.md) ;; *) continue ;; esac
    rel="$f"
    stream+="$(awk -v p="$rel" '{print p":"FNR":"$0}' "$f" 2>/dev/null)"$'\n'
  done < <(git ls-files --others --exclude-standard -- "${surfaces[@]}" 2>/dev/null || true)

  # Drop empty lines produced by the joins.
  stream="$(printf '%s\n' "$stream" | sed '/^$/d')"

  local file_count line_count offenders
  line_count="$(printf '%s' "$stream" | grep -c . || true)"
  file_count="$(printf '%s\n' "$stream" | sed -n 's/^\([^:]*\):.*/\1/p' | sort -u | grep -c . || true)"

  if [ -z "$stream" ]; then
    # No added lines in the worktree/staged/untracked scan. If the committed base
    # was not covered this is under-scanned, not proven clean -> degraded.
    if [ "$degraded" = 1 ]; then
      if emit_clean_result 1 0 0; then return 0; else return $?; fi
    fi
    echo "generic_r0_leak_scan_ok: 0 added markdown line(s) in scope; nothing to scan"
    return 0
  fi

  offenders="$(printf '%s\n' "$stream" | scan_stream)" || return 2
  if [ -n "$offenders" ]; then
    # A leak in whatever WAS scanned always blocks, degraded or not.
    echo "generic_r0_leak_scan: high-signal public leak pattern(s) in added markdown lines:" >&2
    printf '%s\n' "$offenders" | sed 's/^/  /' >&2
    echo "generic_r0_leak_scan_failed: sanitize the line(s) above (use angle placeholders / generic terms), or run the private ALIAS_AUDIT_CMD audit if this is a false positive" >&2
    return 1
  fi
  if emit_clean_result "$degraded" "$line_count" "$file_count"; then return 0; else return $?; fi
}

if ! command -v rg >/dev/null 2>&1; then
  echo "generic_r0_leak_scan_error: missing required command: rg" >&2
  exit 2
fi

case "${1:-}" in
  --self-test) run_self_test ;;
  *) main_scan "${1:-.}" ;;
esac
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