CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reviewable-external-draft

Reconcile source evidence and prepare an accurate external-facing draft without bypassing review

Quality

70%

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 ./resources/skills/communication/reviewable-external-draft/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 tight, well-structured instruction-only skill whose procedure and verification checklist are genuinely clear. Its main weakness is actionability: key execution details are phrased generically ('the available contact source', 'the native draft or document capability') rather than concretely, and discrepancy handling lacks a feedback loop.

Suggestions

Name the concrete contact source and the concrete draft/send capability in steps 3 and 5, or state explicitly how to discover them, so the guidance is executable rather than directional.

Add a short worked example (e.g., a two-line sample external draft with a reconciliation note) to anchor what 'qualify uncertainty' and 'omit internal-only detail' look like in practice.

Add a feedback loop for step 2's unresolved discrepancies (e.g., 'if a correction supersedes a figure, use the latest value and flag the change in the reconciliation notes').

DimensionReasoningScore

Conciseness

The body is lean with zero padding: sections 'When to Use', 'Procedure', 'Pitfalls', and 'Verification' contain only actionable directives ('Draft only claims supported by the collected evidence', 'Do not copy stale figures when a later correction exists') and no explanation of concepts Claude already knows. Every token earns its place, matching the 'lean and efficient' anchor exactly.

5 / 5

Actionability

The six procedure steps give directional guidance but hedge on the concrete specifics an executor needs: 'Resolve recipient identity through the available contact source' never names the contact source, and 'Save or present a reviewable draft through the native draft or document capability' never identifies the capability or gives a worked example. This sits between anchor 2's high-level hints and anchor 4's mostly-executable guidance — real steps, missing key details.

3 / 5

Workflow Clarity

The numbered 'Procedure' is a clearly sequenced six-step process reinforced by an explicit 'Verification' checklist ('Recipient identity and communication mode match the request', 'Dates, figures, status, and commitments map to current source evidence'). It falls short of anchor 5 because there is no error-recovery feedback loop — what to do when step 2's 'unresolved discrepancies' are found is only partially covered by 'Report ... reconciliation notes that require human review', and no fix-and-recheck cycle exists. This is not a destructive or batch operation, so the ≤3 cap does not apply.

4 / 5

Progressive Disclosure

Per the rubric guideline for skills under 50 lines with no need for external references, progressive disclosure can score 5 with just well-organized sections. The ~28-line body has four clean, well-labeled sections and no bundle files exist to reference (references/, scripts/, assets/ are absent), so nothing is inappropriately inlined or buried.

5 / 5

Total

17

/

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 communicates a clear, honest purpose — evidence-grounded external drafting with a review gate — and stays concise without fluff. Its weaknesses are the missing 'Use when...' trigger clause and the absence of natural user vocabulary (email, client update, reply), which leave both completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit trigger clause, e.g., 'Use when preparing an email, reply, or status update for a client, customer, partner, or leadership audience based on internal messages or documents.'

Include the natural words users would actually say — 'email', 'message', 'reply', 'client update' — alongside 'external-facing draft' to improve trigger matching.

Make the 'what' slightly more comprehensive by naming the reconciliation and verification behaviors (e.g., 'check figures against the latest corrections'), which would lift specificity from 1-2 actions to several.

DimensionReasoningScore

Specificity

The description names two concrete actions — 'Reconcile source evidence' and 'prepare an accurate external-facing draft' — but the domain stays abstract ('source evidence' could be anything) and coverage is not comprehensive (no hint of the audience-check, verification, or draft-preservation steps). This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') and falls short of anchor 4's 'several specific actions' with only minor gaps.

3 / 5

Completeness

The 'what' is clearly stated ('Reconcile source evidence and prepare an accurate external-facing draft without bypassing review') but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. This is exactly anchor 3: 'has a clear what but when is missing or only weakly implied'.

3 / 5

Trigger Term Quality

It contains some relevant keywords a user might echo ('external-facing', 'draft', 'review') but misses the natural phrases users actually say when they need this skill — 'draft an email', 'client update', 'reply to the customer', 'status update'. Anchor 3 ('some relevant keywords but missing common variations or synonyms') fits; anchor 4 would require good coverage of those everyday terms.

3 / 5

Distinctiveness Conflict Risk

The 'without bypassing review' qualifier carves out a recognizable niche, but 'Reconcile source evidence and prepare an accurate external-facing draft' would still plausibly collide with generic email-drafting, summarization, or communication skills. Anchor 3 ('somewhat specific but could still overlap with similar skills') is the best fit; anchor 4's 'minor overlap risk with closely related skills' is too generous given the broad drafting domain.

3 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

odysseus-dev/odysseus

Path

resources/skills/communication/reviewable-external-draft/SKILL.md

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.