docs(skills): trigger-first best-practice skill descriptions#27
Merged
Conversation
…st best practice
Rework all 16 core skill descriptions to follow Anthropic's skill-authoring
guidance: each is now a third-person capability statement plus concrete
WHEN-to-use triggers, with the internal-coverage clause ("Covers/Creates/
Explains/Checks/Scans ...") removed.
That clause summarized each skill's workflow, which (a) risks the model
following the description instead of reading the skill body and (b) wastes
always-preloaded metadata budget across all 16 descriptions. The cross-skill
routing redirects for add-skill / add-command / add-agent are preserved so the
routing-overlap validator still passes.
Descriptions shrank from roughly 400-600 to 190-400 characters each; no
component, command, agent, or runtime behavior changed. Refresh the
release-evidence content digest to match the new blobs.
Claude-Session: https://claude.ai/code/session_01Y29c9sJRhChvxDcUjab5Xo
rldyourmnd
force-pushed
the
docs/skills-best-practice-descriptions
branch
from
July 18, 2026 03:27
46eec2d to
a23b71e
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Rewrites all 16
nddev-buildercore skill descriptions to follow Anthropic's skill-authoring best practices: each description is now a third-person capability statement + concrete WHEN-to-use triggers, with the internal-coverage clause (Covers…/Creates…/Explains…/Checks…/Scans…) removed.Why
Anthropic's guidance is explicit: "when a description summarizes the skill's workflow, Claude may follow the description instead of reading the full skill content." The old middle clause did exactly that, and — since all 16 descriptions are preloaded into context at startup — it also wasted always-resident metadata budget. Trigger-first descriptions improve skill selection (the agent picks the right
add-*skill) and keep the body as the single source of procedure.Scope / safety
add-skill/add-command/add-agentare preserved, so the routing-overlap validator still passes.build/release-evidence.jsoncontent digest refreshed to match the new blobs (pending bundle, bound to a stableorigin/mainancestor) — same pattern as docs(skills): scope add-skill to skills, route commands and subagents #23.Validation
validate_zcode_components.py(routing-overlap + ≤1024-char length): PASSvalidate_public_contracts.py(README/version parity): PASSemit_evidence.py --check: valid (decision: pending)https://claude.ai/code/session_01Y29c9sJRhChvxDcUjab5Xo