evidence-prose

Turn supplied accomplishment evidence, career material, and existing drafts into confident, evidence-driven professional prose without hype. Use after evidence has been collected when writing or editing promotion cases, self-reviews, impact statements, interview stories, leadership narratives, pitches, nominations, or executive updates. Preserve factual calibration, distinguish ownership from contribution, make outcomes causal and concrete, and identify missing proof rather than inventing it. For collecting weekly source evidence or appending repo-local period roll-ups, use weekly-recap or brag-summarize instead.

Quality

79%

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 ./evidence-prose/SKILL.md

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.

The body is well-structured and actionable with excellent progressive disclosure, but it carries structural redundancy across its evidence model, writing rules, workflow, and final-check sections that inflates length without adding new guidance.

Suggestions

Consolidate the ownership/outcome/scope/leverage guidance into one authoritative section; have 'Core writing rules', the no-fluff workflow step, and 'Final quality check' reference it instead of restating it, to remove the structural redundancy hurting conciseness.

Add one compact paste-ready prose template per destination (e.g. a STAR-variant skeleton for interview stories) inline or in destination-guidance.md to lift actionability from strong to copy-paste-ready.

Make the workflow's feedback loops explicit (e.g. 'if a claim cannot be classified as Demonstrated, downgrade wording or move it to Evidence gaps') so calibration reads as a validation checkpoint rather than a generic reminder.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the ownership/outcome/scope/leverage principles are restated across 'Core evidence model', 'Core writing rules', the no-fluff workflow step, and the 'Final quality check' list, so it could be tightened rather than being cleanly lean.	3 / 5
Actionability	Provides concrete, actionable guidance — claim-status categories, the Activity→Ownership→Scope→Outcome→Leverage model, before/after prose examples, a removable praise-word list, and per-destination structures — with only minor gaps (no paste-ready templates per destination).	4 / 5
Workflow Clarity	A clearly sequenced 7-step workflow with calibration, a no-fluff pass, and a final quality-check checklist serving as checkpoints; the feedback loops are present but somewhat abstract, keeping it just below the explicit-validate level 5.	4 / 5
Progressive Disclosure	The body is an overview that points to three real, one-level-deep reference files (evidence-model.md, destination-guidance.md, evidence-positioning-principles.md), each clearly signaled with a conditional read trigger, matching the top anchor.	5 / 5
	Total	16 / 20 Passed

Description

87%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 is strong: it states a clear capability, gives explicit use-when triggers across many destination types, and actively disambiguates from sibling skills. Its only gap is a few common synonyms in the trigger list.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Turn…into…prose', 'Preserve factual calibration', 'distinguish ownership from contribution', 'make outcomes causal and concrete', 'identify missing proof'), matching the 'several specific actions; minor gaps' anchor rather than the single-action level 3.	4 / 5
Completeness	Explicitly answers both 'what' (turn evidence into evidence-driven prose) and 'when' ('Use after evidence has been collected when writing or editing promotion cases…'), with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural destination terms ('promotion cases, self-reviews, impact statements, interview stories, leadership narratives, pitches, nominations, executive updates'), but common synonyms like 'performance review', 'accomplishments', and 'brag doc' are absent, so it sits at good-but-not-comprehensive rather than 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (evidence-driven professional prose) with explicit boundary guidance ('For collecting weekly source evidence…use weekly-recap or brag-summarize instead'), minimizing conflict with adjacent skills.	5 / 5
	Total	18 / 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: javiermolinar/dope-brag
Path: evidence-prose/SKILL.md
Commit: 73043c7

Reviewed: 1 day 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.