writing-for-routine

Use when writing the unattended night prompt for a routine after grilling-for-routine, when freezing a deterministic step into a Fixed-step Skill, or when the night prompt needs steps and a done-when.

Quality

75%

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 ./skills/writing-for-routine/SKILL.md

Quality

Content

75%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-organized instruction-only skill with concrete steps, done-when checkpoints, and an explicit validation step. The main gap is redundancy between the inline rules and the closing MUST checklist, and a missing explicit retry loop on validation failure.

Suggestions

Convert the trailing MUST list into a single 'Checklist' that references the body rules rather than restating them, or drop the inline restatements to remove redundancy.

Add an explicit feedback loop after step 4 (e.g., 'If a check fails: fix the file and re-run step 4. Done-when: all checks pass.') to make validation recovery unambiguous.

Move the handoff format detail and example prompt steps into a referenced file to keep SKILL.md as a lean overview and lift progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Lean imperative prose with no explanation of concepts Claude already knows, but the trailing MUST list restates rules already given in the body ('MUST NOT use em dashes', 'MUST NOT assign a second-person identity'), adding mild redundancy.	4 / 5
Actionability	Concrete guidance throughout: numbered steps with done-whens, specific file paths ('~/.dora/harness/<slug>/handoff.md'), a handoff format example, and example prompt steps; absence of code is appropriate for this instruction-only skill.	4 / 5
Workflow Clarity	Steps 1-5 are clearly sequenced with done-when checkpoints and an explicit validation step (step 4: 'Check both files: no second-person identity, no em dashes...'), though an explicit 'if checks fail, fix and re-check' feedback loop is only implicit.	4 / 5
Progressive Disclosure	Well-organized into clear sections (Shape, prompt.md, Tick handoff, Fixed-step Skill, Steps) and self-contained with no nested references, though it runs over 50 lines with no external bundle to offload detail into.	4 / 5
	Total	16 / 20 Passed

Description

75%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 well-structured with explicit, concrete 'Use when' triggers and a distinct internal niche, scoring high on completeness and distinctiveness. Its main weakness is jargon-heavy trigger terms that lack natural synonyms and only modest action specificity.

Suggestions

Add one or two plain-language synonyms alongside the internal terms (e.g., 'night prompt', 'automated run', 'checklist step') so the trigger phrasing is more discoverable.

Broaden the action list slightly (e.g., 'writes prompt.md, freezes reusable steps into a Fixed-step Skill, defines a done-when for each step') to lift specificity beyond two actions.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('writing the unattended night prompt', 'freezing a deterministic step into a Fixed-step Skill') but coverage is narrow and not comprehensive.	3 / 5
Completeness	Explicitly answers both what (writing the night prompt / Fixed-step Skill) and when, with three concrete 'Use when...' trigger clauses ('after grilling-for-routine', 'when freezing a deterministic step', 'when the night prompt needs steps and a done-when').	5 / 5
Trigger Term Quality	Relevant internal keywords ('grilling-for-routine', 'Fixed-step Skill', 'done-when') appear, but these are system jargon with no natural synonyms or variations a user would say outside this internal context.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear internal niche with highly specific triggers tied to 'grilling-for-routine' and 'Fixed-step Skill', making conflict with unrelated skills minimal.	5 / 5
	Total	16 / 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: saif-shines/doraval
Path: skills/writing-for-routine/SKILL.md
Commit: d561c85

Reviewed: 4 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.