CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

performance-review

Structure a performance review with self-assessment, manager template, and calibration prep. Use when review season kicks off and you need a self-assessment template, writing a manager review for a direct report, prepping rating distributions and promotion cases for calibration, or turning vague feedback into specific behavioral examples.

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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-structured, action-first skill: the complete templates and concrete tips make it immediately usable. The main improvements are sequencing the connector data-gathering into the output flow and splitting the three templates into per-mode reference files.

Suggestions

Integrate the 'If Connectors Available' section into each mode's workflow (e.g., a step in the manager mode: pull prior review history from HRIS before drafting), so data-gathering is sequenced rather than floating separately.

Move the three full output templates into per-mode reference files (e.g., references/self-assessment.md, references/manager.md, references/calibration.md) with brief inline summaries, keeping SKILL.md a lean overview.

Delete the redundant line 'Generate performance review templates and help structure feedback.' — it duplicates the frontmatter description and adds no instruction.

DimensionReasoningScore

Conciseness

The three templates are the payload and earn their tokens with essentially no concept-explanation padding, but the redundant intro line ('Generate performance review templates and help structure feedback') and the general-knowledge Tip #2 ('Balance positive and constructive — both are essential') are minor trims that keep it just short of lean.

4 / 5

Actionability

Three complete, copy-paste-ready markdown templates fully cover the three modes, mode invocations are concrete, and the Tips give specific before/after contrasts ('You reduced deploy time 40% by implementing the new CI pipeline' vs. 'Great job') — fully executable guidance for an instruction-only skill.

5 / 5

Workflow Clarity

Mode dispatch is unambiguous ('If no mode is specified, ask what type of review they need') and each mode maps to a complete output, but the 'If Connectors Available' data-gathering steps sit disconnected from the templates with no sequencing of when to pull data or how to fold it into the outputs — a minor gap rather than missing structure.

4 / 5

Progressive Disclosure

Well-organized sections with easy header navigation, and the single reference (CONNECTORS.md) is clearly signaled and one level deep; no bundle files exist to misplace. At ~145 lines with three full templates inline, per-mode reference files would improve the split, keeping it just below the top anchor.

4 / 5

Total

17

/

20

Passed

Description

92%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 description that clearly states concrete capabilities and pairs them with an explicit, scenario-rich 'Use when' clause. The only weakness is modest synonym coverage for trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete deliverables — 'self-assessment template', 'manager template', 'calibration prep' — plus specific sub-actions like 'prepping rating distributions and promotion cases' and 'turning vague feedback into specific behavioral examples', giving comprehensive coverage of the skill's capabilities with no gaps.

5 / 5

Completeness

Explicitly answers both questions: 'Structure a performance review with self-assessment, manager template, and calibration prep' states the what, and an explicit 'Use when review season kicks off...' clause with four concrete trigger scenarios states the when, matching the top anchor's form exactly.

5 / 5

Trigger Term Quality

Good natural keyword coverage — 'review season kicks off', 'self-assessment template', 'manager review for a direct report', 'rating distributions', 'promotion cases', 'calibration' — but common user variations like 'annual review', 'year-end review', '360 feedback', or 'write my review' are missing, so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Clear HR-performance niche with distinct triggers — 'calibration', 'rating distributions', 'promotion cases', 'direct report' are unambiguous performance-review vocabulary with minimal risk of firing for the wrong skill.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

anthropics/knowledge-work-plugins

Path

human-resources/skills/performance-review/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.