impl

Implement a feature. Tirgger when "implement" in the prompt

Quality

67%

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/impl/SKILL.md

Quality

Content

85%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 tight, well-structured orchestration workflow with an explicit validate-fix-retry feedback loop and concrete agent parameters. It is slightly thin on executable command examples for PR mechanics and has several typos, but otherwise earns its tokens.

Suggestions

Fix the typos ('reponse', 'revelant', 'regularily', 'sumarized') and tighten wordy objective statements like 'The objective of the agent is to implement the feature following the project guidelines; implement, build, lint, local testing'.

Add a concrete example (command or snippet) for PR draft creation/updating and for how to launch a subagent, since those mechanics are currently left abstract and are the main actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is lean directive prose with no padding and no explanation of concepts Claude already knows; only minor wordiness in a few objective statements ('The objective of the agent is to implement...') could be trimmed, fitting 'efficient; minor instances of over-explanation' rather than the every-token-earns-its-place bar of 5.	4 / 5
Actionability	Concrete guidance is provided via specific models (gpt-5.6-sol/terra), reasoning levels, a 60000 ms_timeout, and required output fields, but there are no example commands or snippets for PR draft creation or agent launch syntax, leaving minor gaps consistent with a 4.	4 / 5
Workflow Clarity	The five numbered phases include an explicit Validation-agent checkpoint, an 'All checks pass' gate, and a fixup-then-return-to-step-2 feedback loop for error recovery, matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no external references needed and is well-organized into labeled sections (Agents, Rules, Orchestrator response), which the simple-skill scoring note says can score 5 on well-organized sections alone.	5 / 5
	Total	18 / 20 Passed

Description

50%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 answers both 'what' and 'when' with an explicit single-keyword trigger, but it is extremely broad and thin on concrete capabilities, making it likely to conflict with other coding skills. Multiple typos ('Tirgger') and minimal action detail further reduce quality.

Suggestions

Add 2-3 concrete orchestrator capabilities to the description (e.g., 'delegates to implementation/validation/fixup subagents, opens a PR, and drives CI to green') so the 'what' is more than a single vague action.

Broaden trigger terms beyond the single word 'implement' to natural synonyms users say ('build a feature', 'add a feature', 'develop X') and fix the 'Tirgger' typo.

Narrow distinctiveness by stating the PR-orchestration niche (e.g., 'feature PR orchestrator: implements, validates, and ships a feature as a ready PR') to reduce overlap with generic coding skills.

Dimension	Reasoning	Score
Specificity	The phrase 'Implement a feature' names the domain but provides only a single minimal/generic action, matching the 'names the domain but actions are minimal or generic' anchor; it lacks the second concrete action needed for a 3.	2 / 5
Completeness	Both 'what' ('Implement a feature') and 'when' ('Trigger when "implement" in the prompt') are present with an explicit trigger phrase, so it is not capped at 3, but the 'what' is thin and single-action rather than the multi-action list required for a 5.	4 / 5
Trigger Term Quality	'implement' is a natural keyword users actually say, but coverage is a single term missing common variations/synonyms (build, add, create, develop), fitting 'some relevant keywords but missing common variations'; it is above 2 because the term is not generic jargon.	3 / 5
Distinctiveness Conflict Risk	Triggering on the single word 'implement' fires on a large fraction of coding requests, creating high overlap risk with many implementation/coding skills, matching 'very broad; high overlap risk'; it is above 1 because it does name a domain rather than being entirely generic.	2 / 5
	Total	11 / 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: tympanix/Electorrent
Path: .agents/skills/impl/SKILL.md
Commit: 6776815

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.