7405298b4b
- #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 |
||
|---|---|---|
| .. | ||
| .claude-plugin | ||
| commands | ||
| skills/fable-goal | ||
| README.md | ||
fable-goal
Turn a ramble about something you want made into one polished, autonomous /goal prompt — copy-paste ready for a fresh session. The skill writes the prompt, never the build.
What this skill does
You describe an outcome in fragments ("I want like 5 landing pages for my prompt pack, crazy good, put them up somewhere"). The skill:
- Extracts the six slots a goal prompt needs: deliverable, quantity, audience/stakes, tools named, quality bar, destination
- Fills gaps from your brand profile (if you keep one) or sensible defaults — asking at most ONE question batch, never interviewing in rounds
- Verifies before naming — every skill, path, or MCP the prompt mentions is checked against the live environment so the fresh session never chases phantoms
- Writes a 150–350 word flowing-prose prompt with the seven-part anatomy: desire + stakes → quality bar → tool inventory + discovery mandate → creative-freedom grant → verification loop matched to the medium → delivery → goal line + autonomy directive
- Self-checks against six binary criteria before delivering, then outputs the prompt in one fenced block plus a short Assumptions list
The philosophy
Get out of the model's way. A great /goal prompt nails the what, grants explicit freedom on the how, and demands self-verification before done — with a completion condition the session can observe itself (load the page, run the script, watch the render).
Usage
/cs:fable-goal I keep manually sorting the podcast files my editor sends, write me a prompt so a session builds me something for that
Or just ramble and say "turn this into a goal prompt."
Design notes
Unlike sibling productivity/* plugins, this one intentionally ships no agents/ persona and no assets/: the skill is a single reasoning pass with nothing to orchestrate in parallel, invoked via /cs:fable-goal, and its output is one prose block with no templates to fill. scripts/goal_prompt_self_check.py covers the mechanically checkable subset of the pre-delivery self-check (word count, goal line, autonomy directive, verification/freedom/destination language); deliverable concreteness and live-environment resource verification remain author judgment.
Attribution
Derived from duncan-buildroom/freeskills fable-goal ("free to use and modify. Made for builders."). This version is a substantial restructure: wrong-tool check, observable-done principle, verification-defaults-by-medium table, six-point pre-delivery self-check, failure-mode catalog, and a second worked example in a non-web medium.