binary-loop

Iteratively reduce Fallow binary size using cargo-bloat and release-build measurements while preserving features, performance, and compatibility.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/binary-loop/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.

An exceptionally lean, well-structured iterative loop with a genuine keep/reject feedback gate and a clear termination condition. Its main weakness is that the core operations lack executable commands, and the validation step references unspecified 'verification'.

Suggestions

Add the concrete measurement commands, e.g. `cargo bloat --release` and a size-capture step such as `stat -c %s target/release/<binary>` recorded before/after each change.

Specify what "verification passes" means in step 5 (e.g. `cargo test --release` or the project's CI check) so the validation gate is executable.

Show the release-build command with the identical settings referenced in step 4 (e.g. `cargo build --release` with the profile flags) to make the controlled comparison reproducible.

Dimension	Reasoning	Score
Conciseness	The body is 15 lean lines with zero padding — no explanations of concepts Claude already knows, no boilerplate — every line (measurement, selection, bounded change, rebuild gate, loop condition, guardrail) earns its place. It clearly matches the 'lean and efficient' anchor and not the 'minor over-explanation' anchor of 4.	5 / 5
Actionability	Steps are concrete in intent ("Measure the release binary and capture cargo-bloat evidence", "Rebuild with identical release settings") but no executable commands are given for the core operations — no `cargo bloat --release` invocation, build command, or size-capture command. It is not 4 because executable guidance has real gaps, and not 2 because the steps are specific and implementable rather than high-level hints.	3 / 5
Workflow Clarity	The seven steps are clearly sequenced with an explicit keep/reject validation gate ("Keep the change only when size improves and verification passes") and a loop-termination condition, which is stronger than the checkpoint-less anchor of 3. It falls short of 5 because "verification passes" never specifies what verification means (tests? CI?), leaving a minor validation gap.	4 / 5
Progressive Disclosure	This is a simple skill under 50 lines with no need for external references — no references/, scripts/, or assets/ exist — and the body is well organized as a single headed procedure plus a guardrail note. Per the rubric's simple-skill guidance, that merits 5; there is no inline content that belongs in a separate file.	5 / 5
	Total	17 / 20 Passed

Description

65%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 concise, third-person description with a specific niche and concrete tooling, but it omits any 'when to use this' trigger guidance, which caps its completeness and weakens discoverability. Trigger terms are good though missing a few common synonyms.

Suggestions

Add an explicit 'Use when...' clause, e.g. "Use when the user asks to shrink the Fallow binary, reduce build size, or investigate binary bloat."

Include a few natural synonyms or trigger phrasings such as "shrink the binary" or "optimize binary size" to broaden keyword coverage.

Optionally enumerate one more concrete capability (e.g. capturing before/after size deltas) to lift specificity from 1-2 actions toward several.

Dimension	Reasoning	Score
Specificity	The description names the domain and 1-2 concrete actions — "reduce Fallow binary size using cargo-bloat and release-build measurements" plus the constraint "preserving features, performance, and compatibility" — but does not enumerate several specific actions. It is not 4 because it covers fewer distinct actions than the 'several specific actions with minor gaps' anchor, and not 2 because the actions named are concrete rather than generic.	3 / 5
Completeness	The "what" is clear (iteratively reduce binary size with cargo-bloat evidence while preserving behavior), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the "what" is specific rather than vague.	3 / 5
Trigger Term Quality	"binary size", "cargo-bloat", and "release-build" are terms a user with this need would naturally say, giving good keyword coverage. It falls short of 5 because common synonyms like "shrink the binary", "optimize build size", or "bloat" are missing.	4 / 5
Distinctiveness Conflict Risk	"Fallow binary size", "cargo-bloat", and "release-build measurements" carve out a clear niche with essentially no overlap risk against generic skills; it is not 4 because no closely related skill would plausibly trigger for this description.	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fallow-rs/fallow
Path: .agents/skills/binary-loop/SKILL.md
Commit: 74177e5

Reviewed: 5 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.