CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dev

Load when implementing an issue or applying review fixes as a dev agent.

Quality

71%

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 ./skills/dev/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 extremely lean, rule-dense body with concrete commands, a clear workflow spine, and strong validation discipline and failure handling. Its main weaknesses are the missing bundle workflow files the body depends on and compression that intermittently trades clarity for brevity.

Suggestions

Ship the referenced workflow files (workflows/dev-implement.md, workflows/dev-fix.md, workflows/long-running-validation.md) in the skill bundle, since the body delegates its core step sequences and validation gate to them.

Move the dense policy material (Engineering Rules, the rebase-map and loaded-file-rebase rules) into a reference file and keep a short rule index in SKILL.md, so the overview stays navigable.

Unpack the most compressed rules (e.g. the rebase-map reply rule and the PREVIOUS_ROUND_COMMIT diff procedure) into short step lists — the token savings are currently offset by re-read cost.

DimensionReasoningScore

Conciseness

The body is telegraphic with zero padding and no explanation of concepts Claude already knows ("Before adding a function, parser, stub or loop, grep the repo for the verb it performs"). It falls short of the top anchor because the compression occasionally sacrifices clarity — the "rebase-map:" rule and the loaded-file rebase-diff paragraph each require multiple re-reads to unpack.

4 / 5

Actionability

Concrete commands and file shapes appear throughout ("git diff --no-renames --name-only [PREVIOUS_ROUND_COMMIT] HEAD -- <each loaded file's repo path>", the run-notes path format, and explicit --issue/--kind/--validate/--validate-note semantics). Not fully executable overall because the core workflow steps and the dev-return schema are deferred to referenced files that are not present in this bundle.

4 / 5

Workflow Clarity

Sequences are explicit ("activate → plan → implement → validate → commit → QA labels → summary → artifact → return") with a dedicated validation gate, an investigation-run question/answer protocol with a two-inconclusive limit, and interruption handling ("report an interruption without a verdict as failure"). The full step-by-step workflow itself lives in the absent workflows/dev-implement.md, leaving the body at overview-plus-contract level.

4 / 5

Progressive Disclosure

References are one level deep and clearly signaled with section anchors ([dev-implement.md § 5](workflows/dev-implement.md#5-validate), [../orch/references/skill-rules.md](../orch/references/skill-rules.md)), but the skill's own bundle files (workflows/dev-implement.md, workflows/dev-fix.md, workflows/long-running-validation.md) are missing from the bundle, and dense policy sections (Engineering Rules, Round Contract) are inlined that could live in reference files.

3 / 5

Total

15

/

20

Passed

Description

62%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 terse, trigger-first description that clearly states when to load the skill and its two core actions, but keyword coverage is thin and the what-side detail is minimal. It is functional and distinct within its multi-skill ecosystem, yet leaves common trigger phrasings unstated.

Suggestions

Add natural trigger synonyms such as "implement", "code review fixes", "address review feedback", or "fix findings" so the description matches more of the phrasings a caller would actually use.

Briefly expand the what-side (e.g. "plans, implements, validates, and commits the change, then returns a completion artifact") so the description states capabilities explicitly rather than only load conditions.

DimensionReasoningScore

Specificity

"implementing an issue" and "applying review fixes" are two concrete actions, but coverage stops there — no mention of validation, commits, or artifacts. This matches the anchor for 1-2 concrete actions rather than the several-specific-actions level.

3 / 5

Completeness

"Load when implementing an issue or applying review fixes" provides an explicit when-clause and the actions state the what, so both are present. It falls short of the top anchor because the what is terse and merged into the trigger rather than stated separately with concrete capability detail.

4 / 5

Trigger Term Quality

"implementing", "review fixes", and "dev agent" are terms a caller would naturally use, but common variations and synonyms ("address feedback", "code review comments", "fix findings") are missing. Keyword coverage is relevant yet thin, sitting below the good-coverage anchor.

3 / 5

Distinctiveness Conflict Risk

"as a dev agent" implementing issues and applying review fixes carves a niche distinct from sibling reviewer/orch skills, with minor overlap risk. "implementing an issue" is broad enough to overlap with general dev skills, keeping it below the clear-niche anchor.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 6 missing, 14 suspicious

Warning

Total

13

/

16

Passed

Repository

vanillagreencom/kendex

Path

skills/dev/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.