okr
Create quarterly OKRs based on team goals and role. Generates 3 Objectives with 3 Key Results each (9 total), with 70%/100% achievement criteria.
56
45%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/okr/SKILL.mdQuality
Discovery
67%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 excels at specificity and distinctiveness, clearly defining the exact output structure (3 Objectives, 3 Key Results each, achievement criteria). Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Trigger terms are decent but could be broadened to capture more natural user language around goal-setting and planning.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to create OKRs, set quarterly goals, or plan team objectives.'
Include additional natural trigger terms like 'goal setting', 'performance planning', 'KPIs', 'objectives and key results' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating quarterly OKRs, generating 3 Objectives with 3 Key Results each (9 total), and including 70%/100% achievement criteria. Very specific about the output format and structure. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (generates OKRs with specific structure and criteria), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes good terms like 'OKRs', 'team goals', 'Objectives', 'Key Results', and 'quarterly', but misses common variations users might say such as 'goal setting', 'performance goals', 'KPIs', 'planning', or 'objectives and key results' spelled out. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — quarterly OKRs with a specific structure (3x3, 70%/100% criteria) is unlikely to conflict with other skills. The combination of OKR-specific terminology and structural details makes it clearly distinguishable. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a CLI help page than actionable instructions for Claude. It defines a command interface with options but critically lacks example outputs showing what a well-formed OKR looks like with 70%/100% targets, and provides no workflow for how Claude should actually generate the OKRs. The role-specific sections explain domain knowledge Claude already possesses rather than providing unique, actionable guidance.
Suggestions
Add a complete example output showing one Objective with 3 Key Results including concrete 70%/100% targets, so Claude knows exactly what format and quality to produce.
Define a clear step-by-step workflow: parse team goals → identify role-relevant themes → draft 3 objectives → generate 3 KRs per objective with dual targets → validate alignment with team goals → format output.
Remove or drastically condense the role-specific considerations section—Claude already knows what engineers, PMs, designers, and QA professionals focus on. Replace with any non-obvious, project-specific guidance.
Explain what the --interactive and --refine modes actually do in terms of Claude's behavior (e.g., what questions to ask, when to confirm, how to iterate).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably structured but includes some unnecessary padding. The role-specific considerations section explains things Claude already knows (e.g., what engineers or PMs typically focus on), and the option tables are verbose for what could be more compact. | 2 / 3 |
Actionability | The skill describes a command interface but provides no actual implementation logic, no example output, and no concrete instructions for how Claude should generate OKRs. There's no example of what a generated OKR looks like (no sample output with 70%/100% targets), making it impossible to know what to produce. | 1 / 3 |
Workflow Clarity | There is no clear workflow for how Claude should process the input and generate OKRs. The skill lists options and output structure but doesn't sequence the steps (e.g., parse goals → map to role → generate objectives → generate KRs with dual targets → format output). Interactive and refine modes are mentioned but not explained. | 1 / 3 |
Progressive Disclosure | The content is organized with clear sections and headers, which is good. However, the role-specific considerations could be split into a reference file, and the skill references sample files (--sample) without explaining their expected format. No external references are provided for deeper content. | 2 / 3 |
Total | 6 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- sc30gsw/claude-code-customes
- Commit
7aff694
- 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.