bounded-work-item

Execute one scoped implementation or investigation item and return evidence without changing workflow authority.

Quality

69%

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 ./docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.coder/skills/bounded-work-item/SKILL.md

Quality

Content

92%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 an exemplary lean, well-structured instruction skill: a clear sequenced workflow with verification and rework feedback, concrete specifics, and a tight boundaries checklist. Only actionability is marginally short of perfect because guidance is procedural rather than copy-paste executable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; every line earns its place.	5 / 5
Actionability	Provides concrete, specific guidance (the `done\|blocked\|needs_rework` enum, the exact `ask --chain --artifact-reply` operation, "smallest change inside its allowed paths") with only minor gaps typical of policy/process instruction.	4 / 5
Workflow Clarity	A clear numbered 1-6 sequence with an explicit verification checkpoint (step 4) and a rework feedback loop (step 6), plus a Boundaries section acting as a checklist.	5 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with no bundle files needed; the well-organized ## Workflow and ## Boundaries sections satisfy the simple-skill exception for a top score.	5 / 5
	Total	19 / 20 Passed

Description

46%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 states a clear purpose but is abstract and lacks a natural trigger clause, leaving its "when" implicit. It is reasonably distinct from other skills but would benefit from concrete trigger phrases.

Suggestions

Add a "Use when..." clause naming concrete triggers (e.g., when the controller hands off a single scoped work packet).

Replace abstract jargon ("workflow authority", "work packet") with at least one or two natural user-facing terms.

List the concrete actions performed (e.g., read declared refs, make the smallest change, run focused verification, submit evidence) to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ("scoped implementation or investigation item") and a couple of concrete actions ("execute", "return evidence"), but the actions remain fairly abstract rather than a comprehensive list of specific operations.	3 / 5
Completeness	It has a reasonably clear "what" (execute a scoped item and return evidence) but entirely omits a "when"/"Use when..." trigger clause, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	The description relies on technical jargon ("work packet", "workflow authority", "evidence") with no natural phrases a user would say; it lacks common variations or synonyms.	2 / 5
Distinctiveness Conflict Risk	The niche ("one scoped item", "without changing workflow authority") is fairly distinct with minimal overlap risk, though the abstract wording could still brush against general coding skills.	4 / 5
	Total	12 / 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: SeemSeam/claude_codex_bridge
Path: docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.coder/skills/bounded-work-item/SKILL.md
Commit: 01d5b1c

Reviewed: about 20 hours 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.