CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

benchmark-optimization-loop

Turn a user's improvement goal into a bounded benchmark-guided loop: define success and hard constraints, establish a baseline, test one-hypothesis variants, and promote the best measured admissible result with reproducible commands. Use for repeated measured improvements to correctness, quality, task completion, reliability, speed, or cost, including recursive optimization and implementation comparisons.

Quality

84%

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

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-structured, validation-rich process specification with a clear loop, ledger requirements, and promotion gate. It is efficient and actionable, with only minor trimmable redundancy and a slightly long main file that could offload detail to references.

DimensionReasoningScore

Conciseness

The body is dense procedural guidance that assumes Claude's competence and explains no known concepts, but a few points — the repeated independence/no-standard-lowering caveats and some double-stated ledger requirements — could be tightened further.

4 / 5

Actionability

Concrete guidance includes a ledger field specification, a promotion-gate checklist, stop conditions, and illustrative variant tables with commands like 'npm run job -- --batch 500'. The commands are illustrative examples rather than copy-paste executable ones, which is acceptable for a process skill but keeps it below fully executable.

4 / 5

Workflow Clarity

The 8-step numbered loop includes explicit validation checkpoints — reject variants failing hard constraints (step 5), rerun baseline and winner to confirm the delta, and perform the agreed independent acceptance check (step 8) — plus a promotion gate and explicit stop conditions for recursive search, matching the level-5 anchor.

5 / 5

Progressive Disclosure

Sections are clearly organized and the single reference (references/sources.md, verified to exist) is well-signaled and one level deep. The ~150-line body keeps some content inline — notably the Recursive Search detail — that could arguably live in a reference file, leaving minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

83%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 that states a concrete multi-stage workflow and pairs it with an explicit, keyword-rich activation clause. Its only weaknesses are mildly abstract phrasing in a couple of actions and a few missing colloquial trigger synonyms.

DimensionReasoningScore

Specificity

The description lists several concrete actions covering the full loop — 'define success and hard constraints, establish a baseline, test one-hypothesis variants, and promote the best measured admissible result with reproducible commands' — but phrasing like 'define success' stays slightly more abstract than the level-5 anchor's fully concrete action inventory.

4 / 5

Completeness

It explicitly answers both what (the bounded benchmark-guided loop with its four concrete stages) and when ('Use for repeated measured improvements to correctness, quality, task completion, reliability, speed, or cost'), matching the level-5 anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

'Use for repeated measured improvements to correctness, quality, task completion, reliability, speed, or cost, including recursive optimization and implementation comparisons' gives good natural keyword coverage users would say, though common variations like 'faster', 'performance', and 'accuracy' are absent.

4 / 5

Distinctiveness Conflict Risk

'bounded benchmark-guided loop', 'one-hypothesis variants', and 'repeated measured improvements' carve a clear niche with only minor overlap risk against generic benchmark or performance-analysis skills.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

affaan-m/ECC

Path

skills/benchmark-optimization-loop/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.