Stats
Actions
Tags
From sdd
Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec. Triggers when the user asks to write a spec, start a new spec, distill a spec from existing code, add invariants, amend sections (§G, §C, §I, §V, §T, §B), or record a bug via backprop. Common phrasings: "write the spec for...", "new spec", "bug: ...", "amend §V.3", "distill spec from code", "spec this idea". Reads and follows FORMAT.md for the caveman encoding rules and pipe-table shape of §T and §B.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sdd:specThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read `FORMAT.md` at repo root if not already loaded. Glyph skill applies to all writes here.
Read FORMAT.md at repo root if not already loaded. Glyph skill applies to all writes here.
Inspect user request and project state:
SPEC.md at repo root AND args describe idea → NEWSPEC.md AND from-code in args → DISTILLSPEC.md exists AND args start bug: → BACKPROPSPEC.md exists AND args start amend → AMENDSPEC.md exists, no args → ask user which modeInput: user idea.
Steps:
., ids T1…id|date|cause|fix).Write to SPEC.md. Show user full file. Ask: "spec OK? suggest edits or invoke build."
Walk repo. Produce §G (infer from README/package.json/main entry), §C (infer from stack), §I (enumerate public APIs/CLIs/configs), §V (derive from tests and assertions), §T (one task per known TODO or missing test), §B (empty).
Caveman everywhere. Flag uncertain items with ? in text so user can confirm.
Input: bug: <description>.
Steps:
V<next>.B<next>|<date>|<cause>|V<N>.Rule: every bug gets a §B entry. Invariant optional but preferred.
Input: amend §V.3 or amend §T etc.
Read that section. Show current. Ask user what changes. Write. Show diff.
Never silently rewrite sections user did not name.
FORMAT.md.cites column ! list §V/§I deps: T5|.|impl auth mw|V2,I.api.npx claudepluginhub kborovik/pilot-skillsProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.