Skip to content

flurdy/agent-skills / skills/pedantic-review

pedantic-review

Verified

Read-only craft review of changed code and test design: reuse, placement, complexity, and repository conventions. Requirements, coverage sufficiency, execution, and fixes have separate owners.

FileKindSize
SKILL.mdskill md7.7 KB
tests/test-skill-contract.shscript912 B

tests/test-skill-contract.sh

View on GitHub
#!/usr/bin/env bash
set -euo pipefail
SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
SKILL="$SKILL_DIR/SKILL.md"
TEXT=$(tr '\n' ' ' < "$SKILL")
fail() { printf 'FAIL: %s\n' "$*" >&2; exit 1; }
for invariant in 'supplied scope' 'Test design' 'Not assessed here' 'verify-task' 'Do not infer test-writing chronology' 'cannot clear the overall review' 'No automatic fixes' 'read-only' 'gh-pr-snapshot.py'; do
    grep -Fq "$invariant" <<< "$TEXT" || fail "missing craft invariant: $invariant"
done
if grep -Eq 'gh pr diff|test count go up|tests written after|post-hoc|Flag specific uncovered branches|ready for `/create-pr`' "$SKILL"; then
    fail 'craft review still owns coverage chronology or publication'
fi
grep -Fq 'invalidate G2' "$SKILL_DIR/../total-review/SKILL.md" || fail 'later coverage findings must reopen earlier verification'
printf '%s\n' 'pedantic review role contract tests passed'
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall