CC skill-repair
Diagnose and fix failing or degraded skills automatically - systemic-first triage, per-category playbooks, and a verification plan
Diagnose and fix failing or degraded skills automatically - systemic-first triage, per-category playbooks, and a verification plan
As a process C 56/100 · Has gaps — References files that are not bundled: scripts/prefetch-*.sh, scripts/postprocess-*.sh, scripts/*.sh
AnalyzerGitHubSoftware developmentData and analyticsAI and agentstype and topics are labelled automatically from the skill text
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
For the model run — optional
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
net-credential-useSKILL.md:126Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition; documentation table row)| **`sandbox-limitation`** | Usually the "sandbox blocks the network" myth — there is **no** network sandbox. The real cause is a bare `$SECRET` on the command line (refused by the Bash permission lay
detectortable -
low Exfiltration
net-credential-useSKILL.md:255Credential used in a network call (verify the destination is the intended service) (negated — the text forbids it)`gh` and `git` handle auth internally, so the diagnostic reads carry no `$SECRET` on the command line. There is no network sandbox — `curl` works; use `gh api` for GitHub reads, and prefer **WebFetch*
negated
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: scripts/prefetch-*.sh - warning
missing-refreference to a missing file: scripts/postprocess-*.sh - warning
missing-refreference to a missing file: scripts/*.sh
Process rating: all ten parameters 56/100
Will not run. References files that are not bundled: scripts/prefetch-*.sh, scripts/postprocess-*.sh, scripts/*.sh
- 0Tools and files. 3 referenced file(s) missing: scripts/prefetch-*.sh, scripts/postprocess-*.sh, scripts/*.sh
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 31 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3810 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 130: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 31 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.