qtpass-fixing

Bug fixing workflow for QtPass - find, fix, test, PR

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/qtpass-fixing/SKILL.md

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.

The body is highly actionable with executable commands and concrete Bad/Good code patterns organized under a clear workflow, and it includes real validation checkpoints. Its weaknesses are a monolithic structure with a dangling script reference and inlined content that would benefit from being split into reference files.

Suggestions

Move the Common Fix Patterns and Bug Type Playbooks into reference files under ./references/ and link to them, reducing the monolithic SKILL.md body.

Add an explicit re-verify gate (e.g. re-run 'make check') inside the static-analysis amend/force-push loop before pushing.

Create the referenced ./scripts/generate-compile-commands.sh or remove the dangling reference so all cited paths resolve.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with tight code snippets and minimal concept re-explanation, but sections like the filter() prose paragraph and the long Common Fix Patterns list could be trimmed, fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Concrete git/gh/make/clang-format commands and copy-paste-ready C++ Bad/Good pairs cover the common fix cases, matching 'fully executable; copy-paste ready'.	5 / 5
Workflow Clarity	A clear six-step sequence with an explicit Verify checkpoint (make check) and a static-analysis handling loop is present, but the force-push amend loop has no re-test gate before pushing, fitting 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	Headers give structure, but no references/scripts/assets bundle exists, the referenced ./scripts/generate-compile-commands.sh path is missing, and ~20 fix patterns are inlined that could live in reference files, fitting 'some structure but content that should be separate is inline'.	3 / 5
	Total	16 / 20 Passed

Description

58%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.

The description is concise and names a concrete four-step workflow tied to a specific project, but it lacks any explicit 'Use when...' trigger guidance and omits common user phrasings for bugs. These gaps cap completeness and trigger-term quality at the midpoint.

Suggestions

Add a 'Use when...' clause naming concrete user triggers, e.g. 'Use when fixing bugs in QtPass, reproducing reported issues, or preparing a bugfix PR.'

Include natural user phrasings and synonyms (e.g. 'crash', 'failing test', 'broken behavior') to broaden trigger-term coverage.

Clarify scope to reduce overlap with a generic code-fixing skill, e.g. 'for the QtPass password manager codebase'.

Dimension	Reasoning	Score
Specificity	Names the domain ("Bug fixing workflow for QtPass") and lists four concrete actions ("find, fix, test, PR"), matching the 'several specific actions' anchor; not 5 because each action is unexpanded and not 3 because four actions exceed the 1-2 anchor.	4 / 5
Completeness	There is a clear 'what' (a find/fix/test/PR workflow) but no 'Use when...' or equivalent trigger clause, which the rubric caps at 3; not 2 because 'what' is concrete, not 4 because 'when' is entirely missing rather than merely weak.	3 / 5
Trigger Term Quality	"Bug fixing" and "QtPass" are relevant keywords, but common user phrasings like "this crash", "this failing test", or "X is broken" are absent, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Tying the workflow to the specific QtPass project keeps it mostly distinct with only minor overlap risk against a generic code-fixing skill; not 5 because no explicit trigger phrase pins the niche, not 3 because it is project-specific rather than broadly generic.	4 / 5
	Total	14 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: IJHack/QtPass
Path: .opencode/skills/qtpass-fixing/SKILL.md
Commit: 9972a3c

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.