Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →m0n0x41d/h-spec-cover
Surfaces uncovered files in modules that already have recorded decisions — highlights drift before it accumulates and suggests where new decisions are needed. Make sure to use this skill whenever the user asks "is X documented", "what's covered", "spec coverage", "drift detection", "what decisions apply here", "are we tracking this module", "what's undecided in X" — or whenever they are about to modify code in a module with existing DecisionRecords and should be reminded which decisions apply. A
Passed 5 of 11 test cases with the skill, and 2 of 11 without it.
and 2 more in the full report
5 fixed4 passed either way13 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
When framing a problem card for a blind module via tool call, what acceptance criterion parameter value should be specified?
| Checked | Without skill | With skill |
|---|---|---|
| Defines acceptance as having at least one active decision referencing the load-bearing files of the module. | Missed | Passed |
The instructions your model reads when the skill loads.
You are running coverage analysis via mcp__haft__haft_query(action="coverage"). Identifies modules with no decisions (blind) and modules with stale decisions (degraded). Output drives the operator's triage — frame a problem for blind modules, refresh for stale ones.
mcp__haft__haft_query(
action="coverage",
context="<optional context filter>"
)
Returns per-module status:
Within each tier modules are sorted by impact-score descending (per dec-20260527-e4b86938 V1): impact = number of governed modules that depend on this one. A blind module with high impact is high-priority (governed code at risk if it changes); a blind module with zero impact is an isolated utility, low priority. The (impact: N) tag in the output line surfaces the count when > 0; absence of tag = zero impact.
If the operator is currently editing a specific file, prioritize that file's module. Run:
mcp__haft__haft_query(
action="related",
file="<path operator is editing>"
)
Returns decisions whose affected_files include that path. If empty → the file is in a blind module (or governed only at parent module level — check governance_mode).
For each significant gap, recommend the right next action:
/h-frame to record a ProblemCard for the work, then /h-decide after exploration. Without this, the work commission later will see "no decisions" and block./h-verify to baseline+measure the existing decisions before further edits accumulate undeclared drift.test cases passed, vs 2 / 11 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.