CF dsh-trim-cot-leakage
Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as "used to", "no longer", "this cut"; stack or review vantage ("a later PR in this stack", "rejected in review"); reviewer-addressed justifications; control-flow narration; or hedged planning residue in comments, JSDoc, docs, or Agent Notes.
The skill detects traces of unfinished work in code: references like (decision N), audit codes, draft sections with §N. It hunts narrative leaks—"used to be", "no longer", "in the next PR". Flags reviewer-addressed comments and hedged planning.
Audit shows: 72 quality score, 33 process score. Three files, no lint errors, no critical findings. Broken links to missing files. No model runs. Works across nine platforms, Claude and Cursor included.
Useful for pre-deploy code cleanup to catch draft tone and loose ends. Without real-text testing, unclear if it fires on ordinary comments. Worth installing if you specifically need this kind of check.
Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N…
As a process F 33/100 · No process to follow — References files that are not bundled: ../dsh-prose-standard/SKILL.md, ../../notes/archived/process/2026-08-09-committed-artifact-citations.md, ../../../docs/AGENTS.md
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../dsh-prose-standard/SKILL.md - warning
missing-refreference to a missing file: ../../notes/archived/process/2026-08-09-committed-artifact-citations.md - warning
missing-refreference to a missing file: ../../../docs/AGENTS.md - warning
missing-refreference to a missing file: ../../../docs/AGENTS.md - warning
missing-refreference to a missing file: ../dsh-doc/SKILL.md
Process rating: all ten parameters 33/100
- 0Tools and files. 5 referenced file(s) missing: ../dsh-prose-standard/SKILL.md, ../../notes/archived/process/2026-08-09-committed-artifact-citations.md, ../../../docs/AGENTS.md
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 16 mutating operations with no state check
- 100Steps. 22 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1781 tokens
- high The skill tells the model to perform an irreversible action with no human approval
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 445: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 22 items
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.