CtrlK
BlogDocsLog inGet started
Tessl Logo

resolve-fixme

Find all FIXME comments across the codebase and fully implement the work they describe. Use when the user asks to fix, resolve, or address FIXME comments, or when running the "fixme" command. Runs a discovery script to find every FIXME, expands multiline comment blocks, groups related FIXMEs across files into a single implementation task, completes the full underlying code changes, removes the FIXME comments only after the work is done, and verifies that no FIXMEs remain.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, actionable workflow for a batch/destructive task that appropriately includes verification and feedback loops and correctly externalizes its discovery script. Main improvements would be generalizing the hardcoded cargo verify command and tightening the repeated 'don't delete before done' emphasis.

Suggestions

Generalize the verification step: present `cargo insta test --accept` as one example of a project-standard verification command rather than the literal command to run, so the skill applies outside Rust projects.

Consolidate the 'never remove a FIXME before the work is done' guidance into one authoritative callout instead of restating it in step 4, the blockquote, and the Notes.

Make the script reference an explicit navigation signal (e.g., a labeled 'See scripts/find-fixme.sh for discovery behavior' pointer) alongside the inline invocation to strengthen progressive disclosure.

DimensionReasoningScore

Conciseness

Lean, imperative body with no padding of concepts Claude already knows; the only minor trim opportunity is the 'do not remove a FIXME before finishing' rule, which is restated in step 4, the critical-rule blockquote, and the Notes.

4 / 5

Actionability

Provides concrete, executable commands (`bash .forge/skills/resolve-fixme/scripts/find-fixme.sh [PATH]`, `cargo insta test --accept`) backed by a real bundle script, with specific behavioral specs; the only gap is the hardcoded `cargo insta` verify command, which assumes a Rust project.

4 / 5

Workflow Clarity

Clear five-step sequence (discover → expand → consolidate → implement → verify) with an explicit validation checkpoint and feedback loop in step 5 that satisfies the batch/destructive validation requirement; the cargo-specific verify command and slight tension between 'project's standard verification step' and the hardcoded example are minor gaps.

4 / 5

Progressive Disclosure

Well-organized with clear section headers and one correctly split-out bundle file (the discovery script, which exists at scripts/find-fixme.sh) referenced one level deep; the script is invoked inline rather than presented via an explicit 'see X for details' navigation signal, leaving minor organization room.

4 / 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, specific description that clearly states both capability and trigger conditions with concrete user-facing language. Minor room to broaden trigger-term synonym coverage, but otherwise comprehensive and distinct.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'find every FIXME', 'expands multiline comment blocks', 'groups related FIXMEs across files', 'completes the full underlying code changes', 'removes the FIXME comments', 'verifies that no FIXMEs remain' — giving comprehensive coverage in third-person voice.

5 / 5

Completeness

Explicitly answers both 'what' (the full discovery→expand→group→implement→remove→verify pipeline) and 'when' ('Use when the user asks to fix, resolve, or address FIXME comments, or when running the "fixme" command') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user phrases ('fix, resolve, or address FIXME comments', running the 'fixme' command), but coverage is essentially one concept with verb variations rather than a broad synonym set, so it falls just short of the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (FIXME resolution) with distinct triggers including a named 'fixme' command, giving minimal overlap risk with other skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tailcallhq/forgecode
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.