AD codebase-search
Build a persistent semantic vector index over a Python codebase and search it with natural language. Use when an agent needs to find relevant classes, functions, or modules by meaning rather than exact name — e.g. 'find all classes that handle token payments', 'where is rate limiting implemented?', 'which functions process webhook events?'. Also use when setting up codebase-search for the first time on a new repo, rebuilding a stale index, or integrating semantic search into an agentic coding workflow. NOT for exact-string grep (use exec+grep), single-file analysis, or non-Python codebases.
As a process D 46/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 75Steps. 3 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 604 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 597: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.