BF skill-debloater
Diagnoses and slims down bloated, flaky Agent Skills into a lean, stable version. Use when a skill's body has grown too long, burns too many tokens, or has accumulated stale files across versions and behaves inconsistently. The method makes a four-axis decision for every piece of content: WHAT is its nature, WHERE should it live, HOW should it be expressed (prose vs. script), and ALIVE — is it still in use. The first three axes are handled automatically by scripts and the model via lossless reorganization (push down / externalize / merge); the fourth axis, deletion, depends on history only the user knows, so it must be confirmed with the user item by item — default to keep, never auto-delete. Trigger this when the user asks to debloat, slim down, clean up old versions, or when a skill is too long/verbose or flaky.
Diagnoses and slims down bloated, flaky Agent Skills into a lean, stable version.
As a process F 46/100 · Will not run — References files that are not bundled: scripts/audit_skill.py, scripts/scan_how.py
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Diagnoses and slims down bloated, flaky Agent Skills into a lean, … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
missing-refreference to a missing file: scripts/audit_skill.py - warning
missing-refreference to a missing file: scripts/scan_how.py
Process rating: all ten parameters 46/100
- 0Tools and files. 2 referenced file(s) missing: scripts/audit_skill.py, scripts/scan_how.py
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 21 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 85Steps. 19 steps, 2 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2815 tokens
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)
- +3Description length 825: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.