scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-09-07 08:26:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
1506 commits 6 branches 7 tags 43 MiB
Commit graph

4 commits

Author SHA1 Message Date
Claude
08740d4ec2
fix(stream): post-merge required changes for PRs #895/#926/#942/#943/#944/#965 + counter true-up + #964 guard + #954 doc drift 
Applies every pre-merge required change from audit/pr-stream-2026-08/ that
could not land on contributor forks, plus the stream's cross-cutting fixes:

- stock-analysis (#944): description trimmed 1463 -> 1001 chars; Anti-Patterns
  + Cross-References sections added; security-auditor false positive at
  holdco-assetmgr.md:58 suppressed inline (auditor:ignore-line) -> strict PASS
- deepread (#965): renamed research/dsh-deepread -> research/deepread; H1 and
  name updated; research-summarizer cross-ref path-qualified; 12 cited sources
  added across both references; plugin.json + marketplace entry; routed in the
  research orchestrator (SKILL.md registry + SIGNALS + classifier.py in
  lockstep, verified: 'deeply read this pdf' -> deepread, 3 signals)
- business-name-fit (#926): 'Use whenever' -> 'Use when' (validator trigger
  regex); +2 cited sources (USPTO TMEP §1209, Usunier & Shaner 2002) -> 5
- embedded-iot-mentor (#942): references/hardware-selection.md (7 sources,
  datasheet-anchored) + worked mini-example; validator length gate now passes
- swedish-mentor (#943): references/swedish-resources.md (6 sources, stable
  official URLs only); session recipes, milestones, learner situations,
  worked example; mandated opener softened to guidance; plugin.json +
  marketplace entry; validator length gate now passes
- Related Projects (#895): LinkedIn Skills row trued up (10 -> 11 skills,
  hardcoded star count dropped)
- check_plugin_json.py: marketplace description <= 1024 guard added to --all
  (the #964 regression guard; commercial-skills sits at 1021/1024)
- #954 doc drift: quality_gates_for_skills.md, cs-skill-author.md,
  security-guidance SKILL.md now point attribution at authoring-notes.json
- Counter true-up after the 6-skill merge batch: 370 skills / 672 tools /
  809 refs / 92 plugins across README.md badge+table, CLAUDE.md, marketplace
  metadata (derive_counters.py --check passes)

All gates green locally: frontmatter 0 errors, model freshness 0 findings,
dual-publish 0 drifted, paths 0, smoke 0 failed, plugin-json 0 FAIL.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Bzm6Pafyxja6g4jUDPcei
 2026-08-21 09:01:24 +00:00
Claude
7405298b4b
fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 
- #954: strip non-spec source/attribution keys from all 39 plugin.json
  manifests so Claude Code's validator accepts them; metadata preserved in
  new .claude-plugin/authoring-notes.json sidecars; check_plugin_json.py now
  hard-fails manifests carrying those keys and sanity-checks the sidecar;
  CLAUDE.md ClawHub schema section updated to the new rule.
- #949: move the c-level-agents plugin out of c-level-advisor/ to a
  top-level directory so the two marketplace sources no longer overlap;
  updated marketplace.json source, homepage, descriptions, all
  cross-references, docs, harness manifest, mirror-tree symlinks/indexes,
  and rebased the moved files' relative links; domain counters trued up
  (18 -> 19 domains).
- #933: replace dead links to the gitignored maintainer-local megaprompts/
  tree with annotated plain-text references (44 files: SKILL.md, READMEs,
  agents, commands).
- #931: DynamoDB on-demand pricing updated to post-Nov-2024 rates
  ($0.625/M writes, $0.125/M strongly consistent reads).
- #969: skill_security_auditor.py and the three dossier scripts reconfigure
  stdout/stderr to UTF-8 (errors=replace) so legacy Windows codepages no
  longer crash at print time; PYTHONUTF8=1 documented.
- #968: Windows Notes section in INSTALLATION.md + README pointer for the
  core.symlinks mirror-tree checkout caveat.
- #924/#885 residuals: hook commands quote "${CLAUDE_PLUGIN_ROOT}" paths in
  all plugin hooks.json/settings.json (space-safe roots); removed the stale
  pre-rename status/review mirror symlinks and index entries left over from
  the memory-status/memory-review rename.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qgc6RYXWJPr5oW9DHU7zR4
 2026-08-21 05:47:37 +00:00
Claude
3db7dab15f
chore(versioning): unify remaining 20 plugins to 2.9.0 
PR #756 normalized most marketplace versions to 2.9.0, but 20 newer
plugins (added after the normalization pass) remained on their own
versions on both marketplace.json and their plugin.json. Bump them all
to 2.9.0 so the registry advertises one unified release version, with
marketplace.json and every plugin.json fully in sync (62/62 at 2.9.0).

https://claude.ai/code/session_01JGwZR83iSg59EAtpTSCBjH
 2026-05-27 14:25:08 +00:00
Claude
218b973f81
feat(v2.7.3): port aeo-box — AEO skill + security-guidance hook + master prompt preserved 
The user asked us to move everything from alirezarezvani/aeo-box into this
repo, audit every part, rebuild improved, polish for human users.

Audit identified 4 distinct components in aeo-box:

1. **AEO Skill** (`answer-engine-optimization/`) — 9 Python modules, 2,464
   LOC, comprehensive SKILL.md. Real value: Answer Engine Optimization is
   its own discipline distinct from SEO.

2. **Security-guidance hook** — David Dworken's MIT-licensed PreToolUse
   hook catching 9 security anti-patterns in Edit/Write/MultiEdit. Hook-
   based plugin pattern we don't have in our repo yet.

3. **Agentic AEO master prompt** — 1,579-line spec for a multi-agent
   AEO application using Claude Agent SDK. Future-work spec.

4. **Generic dev infra** — 11 generic agents + 9 generic commands +
   GH workflows + TS scripts. We already have equivalents; not worth
   porting.

**This PR delivers 1, 2, and 3** (skipping 4 as planned).

## 1. AEO Skill — `marketing-skill/skills/aeo/`

Distilled 9-module Python toolkit into 3 stdlib CLI tools per
claude-skills convention:

- `aeo_audit.py` (445 LOC) — E-E-A-T + structure scoring across 4
  dimensions + structure. Composite 0-100 with letter grade. 8 industries
  with calibrated thresholds (healthcare/finance/legal 85+ for YMYL;
  saas/b2b/media 70; ecommerce 65). Industry-aware top-fix
  recommendations.

- `aeo_optimizer.py` (252 LOC) — Generates AEO-improved variants in 3
  modes: conservative (schema + footer only), balanced (citation markers
  + heading restructure + schema), aggressive (fact-first lede + full
  restructure). Schema.org Article + FAQPage JSON-LD auto-generated.

- `citation_tracker.py` (310 LOC) — Local-first citation ledger at
  ~/.aeo-data/citations.json. add/list/report/export actions. Computes
  per-URL stats: citation count, LLM coverage, velocity, top queries,
  verdict (EARLY/EMERGING/STRONG).

Plus:
- `SKILL.md` — Path-B-style spec with workflow, industry table,
  anti-patterns, dependencies
- 3 references citing 8 sources each:
  - `aeo_eeat_canon.md` — E-E-A-T methodology for AI citation
  - `llm_citation_patterns.md` — per-LLM citation behavior
    (Perplexity, ChatGPT, Claude, Gemini, Mistral)
  - `aeo_vs_seo.md` — strategic choice between disciplines
- `cs-aeo` agent persona — pragmatic content strategist; refuses fake
  authority signals; insists on real first-person evidence
- `/cs:aeo` command with audit/optimize/track/report/export actions

All 3 scripts smoke-tested:
- aeo_audit --sample → 43/100 (F) on intentionally-weak sample content
- aeo_optimizer --sample → schema injected + corrections footer added
  + bold-paragraphs promoted to H3 + 1 citation marker
- citation_tracker --sample → 4-event sequence (add → list → report
  → export), verdict EMERGING with 4 citations across 3 LLMs

## 2. Security-guidance hook — `engineering/security-guidance/`

PreToolUse hook ported from David Dworken's MIT implementation. Preserves
the 9 upstream patterns verbatim + adds 3 new patterns:

| Pattern | Upstream | Added |
|---|:-:|:-:|
| GitHub Actions workflow injection | ✓ | |
| child_process.exec / execSync | ✓ | |
| new Function | ✓ | |
| eval() | ✓ | |
| dangerouslySetInnerHTML | ✓ | |
| document.write | ✓ | |
| .innerHTML = | ✓ | |
| pickle | ✓ | |
| os.system | ✓ | |
| subprocess shell=True | | ✓ |
| SQL via f-string or .format | | ✓ |
| yaml.unsafe_load | | ✓ |

Modifications from upstream:
- Debug log moved from /tmp to ~/.claude/security-warnings-log.txt
  (persists across reboots)
- Restructured as claude-skills plugin with `attribution` block in
  plugin.json (matches caveman/grill-me/grill-with-docs pattern)
- Added comprehensive reference doc: pretooluse_hook_canon.md
  (8 sources on hook design discipline)

Hook smoke-tested:
- eval(input()) in Write → exits 2 (BLOCK) with stderr warning ✓
- json.loads(input()) in Write → exits 0 (clean) ✓
- subprocess.run(cmd, shell=True) fresh session → exits 2 ✓
- subprocess.run(cmd, shell=True) cached session → exits 0 ✓
  (correct UX: warned once, don't nag)

## 3. Master prompt preserved — `megaprompts/14-aeo-agentic-megaprompt.md`

The 1,579-line multi-agent AEO application spec preserved verbatim as
megaprompts/14 — the next slot after 13-research-megaprompt.md. Path-B
option open for future "build the full agentic AEO app" work.

## Cross-platform sync

- marketplace.json: 55 → 57 plugins (`aeo` + `security-guidance`)
- .codex/skills-index.json: 303 → 305 entries (both new skills indexed)
- .codex/skills/: aeo + security-guidance symlinks created
- .gemini/skills-index.json: 353 → 355 entries
- .gemini/skills/aeo, .gemini/skills/security-guidance: directory mirrors
- .hermes/skills/claude-skills/: re-synced (now includes both new skills
  with relative symlinks)

## What's NOT ported (intentional)

- 11 generic agents from aeo-box .claude/agents/ — we have equivalents
  (cs-code-reviewer, cs-senior-engineer, cs-skill-author)
- 9 generic commands from .claude/commands/ — we have /git:cm /git:cp
  /cs:write-a-skill, etc.
- GitHub workflow YAMLs — repo-specific
- TS scripts (auto-close-duplicates, backfill-duplicate-comments) — GH
  issue management, not a skill

Documented this skip-list in the AEO SKILL.md `Source` block + the
security-guidance plugin.json `attribution` block.

## Honest BYO-sync clarifier for Hermes (folded in from prior work)

Earlier merged PR #678 upgraded Hermes Agent integration to first-class
technical support (committed .hermes/ tree, fixed sync script, relative
symlinks). The earlier docs sweep added an install/configure walkthrough
that wasn't in scope for that PR but caught a user-flagged gap. That doc
section is also in this commit (137 lines added to docs/integrations.md
covering: Hermes-itself install steps, first-run walkthrough,
configuration tips, 6 troubleshooting Q&A).

Verification:
- All 3 AEO scripts pass --help and --sample
- Security hook correctly exits 2 on detection, 0 on cached/clean
- All 3 cross-platform syncs ran clean
- marketplace.json: 57 plugins, all required fields, no duplicates
- 13 v2.7.0 + 13 new files for AEO + 6 new files for security-guidance
  + 1 megaprompt + 1 docs update

https://claude.ai/code/session_01FEUmeuYhmnxVFq7EZM8ZSw
 2026-05-17 06:27:57 +00:00