CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pair

Guided pair-programming mode where Claude teaches rather than writes code, ensuring engineers learn while building

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./tiles/crafter/skills/pair/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is a strong, highly actionable instruction skill: it defines an explicit workflow with real checkpoints, gives verbatim phrasings for the situations that matter, and stays lean by teaching policy rather than general knowledge. The only weaknesses are minor — some duplicated strictness/familiarity calibration content and a single-file layout that is slightly long for a SKILL.md body.

DimensionReasoningScore

Conciseness

The body prescribes novel behavioral policy (strictness boundaries, hint escalation, redirect scripts) rather than explaining concepts Claude already knows, so nearly every section earns its place. Minor trimmable duplication exists — the strictness levels are stated twice (the 1.1 table and "Strictness Enforcement") and "Complexity Calibration" partially restates the familiarity table — which keeps it below anchor 5.

4 / 5

Actionability

As an instruction-only skill, the guidance is fully executable: copy-paste-ready session-start and exit-summary templates, verbatim Socratic questions, a concrete hint-escalation table, scripts for handling "just write it for me" and frustration, and explicit good/bad examples of next steps that cover the common cases.

5 / 5

Workflow Clarity

A clearly numbered three-phase workflow (initialization with strictness/familiarity/context substeps, guided session loop, exit summary) with explicit checkpoints: the session-start confirmation template, error-recovery guidance in "Handling Common Situations", and the "Next Steps Quality Check" validation. This is a conversational skill, so the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist and the single ~180-line file is well organized with clear section headers and navigable substeps. However, it is not a sub-50-line simple skill, and content like "Task-Specific Guidance Patterns" or the JIRA context handling could plausibly live in a reference file — so it falls just short of anchor 5 while remaining comfortably above anchor 3.

4 / 5

Total

18

/

20

Passed

Description

61%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 distinctive behavioral niche clearly and concisely, but it only answers "what" — it never says when Claude should enter this mode. Adding an explicit "Use when..." clause with the natural trigger phrases would lift both completeness and trigger coverage.

Suggestions

Add an explicit activation clause, e.g., "Use when the user asks to pair, be taught or mentored rather than have code written for them, or wants to learn while building."

Include more natural trigger synonyms in the description ("mentor me", "walk me through it", "explain instead of writing") alongside "pair-programming".

Name 1-2 more concrete capabilities in the description (e.g., adjustable strictness levels, session-end learning summaries) to improve specificity.

DimensionReasoningScore

Specificity

The description names the domain ("Guided pair-programming mode") and 1-2 concrete behaviors ("Claude teaches rather than writes code", "engineers learn while building") but coverage is not comprehensive — strictness levels, hint escalation, and session summaries are absent. It is more concrete than anchor 2 (which has only a domain name) but does not list the several specific actions required for anchor 4.

3 / 5

Completeness

The "what" is clear (a guided pair-programming mode where Claude teaches instead of writing code), but there is no "Use when..." clause or equivalent explicit trigger guidance — "ensuring engineers learn while building" states purpose, not when to activate. Per the judging guidelines, a missing 'when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

"pair-programming", "teaches", and "learn" are phrases users would naturally say when they need this skill, giving good keyword coverage. A few natural terms are missing (e.g., "mentor me", "walk me through it", "explain instead of writing"), so it falls short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The teach-not-write pairing mode is a clear niche with distinctive framing. Minor overlap risk remains because teaching-oriented phrasing could collide with general explanation or tutoring skills, keeping it below anchor 5.

4 / 5

Total

14

/

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

ericjohnolson/tessl-test

Path

tiles/crafter/skills/pair/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.