CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-for-agents

Levers for writing documents an agent consumes: context pointers, the two loads, information hierarchy, progressive disclosure, completion criteria, leading words, and pruning. Use when creating or editing a skill, an agent definition, an instruction file, AGENTS.md, or CLAUDE.md.

61

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./src/orchestrator/skills/writing-for-agents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

A well-organized conceptual reference that delivers concrete, directive guidance with worked examples and clean self-contained structure. Its weaknesses are conciseness (some abstract prose that could be tightened) and the absence of any sequenced workflow with checkpoints, which is expected for a reference but caps workflow_clarity.

Suggestions

Tighten the abstract philosophical asides and restated definitions (e.g. 'Attention thins across the excess. The cure is the ladder.') into terse directive sentences so every token drives an action.

If a canonical writing/editing workflow is intended, add a short ordered sequence with explicit completion criteria (e.g., 1) sharpen pointers, 2) tier the ladder, 3) prune no-ops) so the reference doubles as a runnable checklist.

Consider splitting the dense ~80-line body's longer lever definitions behind one-level-deep reference files (e.g. a LEVERS.md) to lift progressive_disclosure to the top anchor while keeping SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

The body is dense and largely earns its tokens by introducing the author's own framework terminology rather than common knowledge, but several abstract philosophical asides ('Attention thins across the excess. The cure is the ladder.') and restated definitions could be tightened, matching the 'mostly efficient but could be tightened' anchor rather than the lean anchor above.

3 / 5

Actionability

Concrete, directive guidance appears throughout ('Front-load the leading word', 'One trigger per branch', 'delete the whole sentence rather than trim words', 'push behind a pointer what only some branches reach') with worked examples ('fast, deterministic, low-overhead' becomes *tight*), giving mostly actionable instruction-level guidance with only minor gaps.

4 / 5

Workflow Clarity

This is a reference rather than a sequenced workflow, so there is no ordered procedure with validation checkpoints; the sectioned structure provides loose organization but no explicit sequence, fitting the 'sequence present but checkpoints missing' band — appropriate for a non-workflow reference, hence not penalized to the lower anchor.

3 / 5

Progressive Disclosure

A single self-contained SKILL.md with clean top-level overview and well-organized section headers, no nested external references (the one outbound link is attribution), and no bundle files to navigate; at ~80 lines it exceeds the simple-skill auto-5 threshold, so good structure with minor organization gaps lands it at 4 rather than 5.

4 / 5

Total

14

/

20

Passed

Description

83%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 strong, third-person description that pairs an explicit 'what' (the enumerated writing levers) with a concrete 'Use when' trigger clause naming real filenames. Trigger-term coverage and distinctiveness are very good rather than fully comprehensive.

DimensionReasoningScore

Specificity

Names the domain ('writing documents an agent consumes') and lists seven concrete levers (context pointers, the two loads, information hierarchy, progressive disclosure, completion criteria, leading words, pruning) — several specific items with comprehensive coverage, though they are concepts/levers rather than discrete actions, placing it just below the fully-comprehensive anchor.

4 / 5

Completeness

It explicitly answers both 'what' (the levers for writing agent-consumed documents, enumerated) and 'when' ('Use when creating or editing a skill, an agent definition, an instruction file, AGENTS.md, or CLAUDE.md.') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use when' clause surfaces natural terms users actually say — 'skill', 'agent definition', 'instruction file', 'AGENTS.md', 'CLAUDE.md' — including the real filenames; a few natural synonyms like 'documentation' or 'docs' are missing, so it falls short of the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The trigger set (AGENTS.md, CLAUDE.md, skill, agent definition, instruction file) carves a clear niche with low conflict risk, but the broad 'writing documents' framing has minor overlap risk with general documentation/writing skills, keeping it just below the minimal-conflict anchor.

4 / 5

Total

17

/

20

Passed

Validation

100%

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
monkilabs/opencastle
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.