* feat(evals): backfill eval manifests for unevaluated methodology hubs (#237)
Add schema-v1 evals/evals.json manifests (>=5 output-quality cases each,
canonical assertions field) to the 16 remaining named skills from issue
#237 plus 11 high-reference unevaluated skills from the issue priority pool.
Raises schema-valid eval coverage from 44/132 (33.3%) to 71/132
(53.8%), clearing the 50% CI-fail threshold.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
* fix(evals): reword expectations prose in agent-skills eval manifest
Replace four prose strings in agent-skills/evals/evals.json that contained
the literal word "expectations" (two in expected_output, two in assertions)
with wording that preserves the meaning (assertions is the canonical field;
a non-canonical alias must not be used) but avoids the substring, so the
mission contract's VAL-M6-503 check passes on every changed manifest.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
---------
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Each README is written for a human audience, explaining:
- What the skill does (not what format it follows)
- What benefit the user gets from installing it
- Quick setup and usage patterns
- When to load/trigger the skill
- What scripts, references, and templates it ships
data-scientist already had a README — left unchanged.
48 READMEs added across all skill and bundle directories.
Adapted from obra/superpowers (Jesse Vincent, MIT) and expanded with
real-world debugging patterns from production use. Core additions:
Phase 1 sub-steps for common failure modes:
- Schema/environment divergence (test vs production schema diffing)
- Exception type specificity (sibling exception traps in Pyhton)
- Progressive characterization grid (isolate retrieval failures variable by variable)
- Dependency source detection (editable dev forks causing schema drift)
- Systematic web research protocol (structured search before guessing)
- macOS sandboxed app debugging (containers, XPC, TCC, iCloud sync)
- Trace data flow upstream from the symptom
Key heuristics:
- Rule of Three: 3+ failed fixes = question the architecture
- Red Flags table: 12 rationalizations to catch yourself making
- Investigation Flow: keep pushing, don't break momentum to ask questions
Includes two worked example references (dev fork detection, macOS Books.app).
Signed-off-by: Jasper <magnus@groktop.us>
