CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qa-recon-risk-map

Map a product's journeys, roles, states, integrations, and recent changes into a risk-ranked coverage matrix with test case IDs. Use after preflight and before executing tests, or when asked what to test.

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable recon procedure with concrete commands, ID formats, and explicit exit criteria. Its main defects are a dangling reference to a bug-pattern library file that is not present in the bundle and an under-specified numeric risk-scoring scheme.

Suggestions

Ship the referenced `01-BUG-PATTERN-LIBRARY.md` in the bundle (e.g., under references/) and reference it with its path, since step 6 and the Pitfalls section's "pattern A1" both depend on content that does not exist in the skill's directory.

Define a numeric scale for the risk formula (e.g., impact 1-5 × likelihood 1-5 with a tie-breaker) so matrix cells get reproducible, comparable scores.

Add a short feedback step for unmet exit criteria, e.g., if any row lacks a risk score or planned skill, revisit steps 4-5 before proceeding to test execution.

DimensionReasoningScore

Conciseness

The body is ~24 lean lines: each procedure step is a single actionable line (e.g., "Pull history: `git log --since=30.days`, open issues, and earlier QA reports"), with no explanations of concepts Claude already knows and no padding — every token earns its place, matching the anchor-5 example's leanness.

5 / 5

Actionability

Mostly executable guidance with concrete specifics (the `git log --since=30.days` command, the ID format example `PAY-03-mobile-webkit`, a sample journey line, and enumerated impact/likelihood factors); it falls short of 5 because the risk formula lacks a numeric scoring scheme and step 6 directs reading `01-BUG-PATTERN-LIBRARY.md`, which is absent from the bundle, leaving a key executable gap.

4 / 5

Workflow Clarity

The 8-step procedure is clearly sequenced (read requirements → enumerate surfaces → journey → matrix → score → patterns → history → assumptions) with an explicit exit-criteria checklist ("The matrix has IDs, risk scores, and a planned skill per row"); it is not 5 because step 6 depends on the missing bug-pattern file and there is no recovery guidance when exit criteria are unmet.

4 / 5

Progressive Disclosure

The short body is well organized into Procedure / Exit criteria / Pitfalls and would otherwise merit a high score, but its single external dependency — "Read `01-BUG-PATTERN-LIBRARY.md`", even cited as "(pattern A1)" in Pitfalls — dangles: no references/ directory or such file exists in the bundle, so the referenced content cannot be navigated to; this is worse than anchor 4's minor organization gaps but better than anchor 2's inlining problem.

3 / 5

Total

16

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states a concrete, multi-faceted capability with a tangible output artifact and an explicit, well-sequenced trigger clause in third-person imperative voice. The only weakness is modest trigger synonym coverage (e.g., no "test plan", "QA", or "coverage" phrasing).

DimensionReasoningScore

Specificity

"Map a product's journeys, roles, states, integrations, and recent changes into a risk-ranked coverage matrix with test case IDs" enumerates concrete inputs (journeys, roles, states, integrations, recent changes) and a concrete deliverable (risk-ranked matrix with test case IDs), matching the anchor-5 comprehensiveness; it is not 4 because coverage of the skill's actions is complete rather than having minor gaps.

5 / 5

Completeness

It explicitly answers both "what" (map journeys, roles, states, integrations, and recent changes into a risk-ranked coverage matrix with test case IDs) and "when" ("Use after preflight and before executing tests, or when asked what to test") with concrete trigger phrasing, a clear anchor-5 match; the "when" clause is explicit, not merely implied, so it is above the anchor-4 example.

5 / 5

Trigger Term Quality

Phrases like "executing tests", "what to test", and "preflight" are natural things a user would say, giving good keyword coverage; it stays at 4 rather than 5 because common variations such as "test plan", "QA", "coverage", or "risk assessment" are absent.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear QA-recon/risk-mapping niche and explicitly positions itself "before executing tests", which distinguishes it from test-execution or bug-reporting skills and leaves minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

itsablabla/qa-bug-agent-skills

Path

skills/qa-recon-risk-map/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.