CtrlK
BlogDocsLog inGet started
Tessl Logo

fusion-issue-solving

Handles GitHub issue resolution end-to-end for prompts like "solve #123", "lets solve #123", "work on #123", "work on https://github.com/owner/repo/issues/123", or by pasting a direct GitHub issue URL as the request. USE FOR: solve #123, continue work on issue #123, work on https://github.com/owner/repo/issues/123, paste a GitHub issue URL for implementation work. DO NOT USE FOR: issue drafting only, PR review only, or non-implementation research.

65

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/fusion-issue-solving/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 a well-sequenced, actionable workflow with strong validation checkpoints, mutation confirmation gates, and a real, properly linked checklist asset. Its two weaker spots are token efficiency (duplicated trigger list between frontmatter and body) and disclosure structure (the dense low-token GitHub strategy could move to a reference file to slim the main body).

DimensionReasoningScore

Conciseness

The body is lean and imperative, assumes Claude's competence (never explains what worktrees or rate limits are), and every operational rule is project-specific knowledge Claude wouldn't have. Minor trimming opportunities remain — the 'When to use' trigger list restates the frontmatter description nearly verbatim, and a few sub-bullets in the low-token strategy could be consolidated — so it fits 'efficient; minor instances of over-explanation' rather than 'every token earns its place'.

4 / 5

Actionability

Concrete, executable guidance throughout: exact draft file naming ('.tmp/pr-body-issue-123-scope-summary.md', not a shared '.tmp/pr-body.md'), a specific template source ('.github/pull_request_template.md'), and quantified API budgets (~20 MCP read calls, ~5 mutations, 5 secondary-limit points per mutation). Validation steps delegate to repo-specific commands by design but remain slightly abstract ('Run targeted checks first, then required project checks'), keeping it below fully copy-paste-ready.

4 / 5

Workflow Clarity

A clear 10-step numbered sequence with an explicit validation checkpoint and feedback loop ('If checks fail, fix relevant issues and re-run before proceeding'), confirmation gates before every mutation ('Before any GitHub mutation... ask for explicit user confirmation'), and a checklist asset for the complex process. This matches the top anchor: explicit validation steps, error-recovery loops, and a checklist.

5 / 5

Progressive Disclosure

The one bundle file (assets/issue-solving-checklist.md) exists, is one level deep, and is clearly signaled from a dedicated Assets section. Structure is good, but the ~120-line body keeps substantial operational detail inline — notably the eight-bullet low-token/rate-limit strategy — that would fit a reference file, matching 'good structure; most content appropriately placed; minor organization gaps' rather than the cleanest split.

4 / 5

Total

17

/

20

Passed

Description

76%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 has excellent trigger coverage and explicit use/don't-use boundaries that make it highly discoverable and distinguishable from adjacent skills. Its main weakness is a thin capability statement: 'Handles GitHub issue resolution end-to-end' says little about what the skill actually does (research, implement, validate, prepare PR). Adding a short list of concrete actions would raise both specificity and completeness.

Suggestions

Enumerate 2-4 concrete capabilities after the domain, e.g. 'Researches the issue, implements a scoped fix, runs validation, and prepares a PR-ready summary' — this would move specificity from generic single-action toward the comprehensive anchors.

Fold the key sub-actions into the 'what' clause so both halves of the completeness anchor (what AND when) are equally concrete, rather than front-loading all specificity into the trigger list.

Trim the duplicated trigger enumeration (the 'USE FOR' list largely restates the 'prompts like' list) to free tokens for capability detail without losing discoverability.

DimensionReasoningScore

Specificity

The description names the domain ('GitHub issue resolution end-to-end') but the capability statement is a single generic action — no concrete actions such as implement, validate, or prepare PR are listed. All the concrete material consists of trigger phrases rather than capabilities, matching the anchor for 'names the domain but actions are minimal or generic'.

2 / 5

Completeness

Both 'what' ('Handles GitHub issue resolution end-to-end') and 'when' ('USE FOR: solve #123, continue work on issue #123...') are explicitly present, and the when-clause includes concrete trigger phrases. The 'what' is high-level rather than enumerating the work performed, placing it between the anchor requiring a fully comprehensive what-and-when pair and the anchor where only 'when' could be more explicit.

4 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and URL forms: 'solve #123', 'lets solve #123', 'work on #123', 'continue work on issue #123', 'work on https://github.com/owner/repo/issues/123', and pasting a direct issue URL. No common variation a user would say is missing.

5 / 5

Distinctiveness Conflict Risk

Clear niche (end-to-end issue implementation) with explicit negative boundaries ('DO NOT USE FOR: issue drafting only, PR review only, or non-implementation research') that sharply reduce overlap risk with adjacent authoring/review skills. Triggers are distinct and unlikely to fire the wrong skill.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
equinor/fusion-framework
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.