CtrlK
BlogDocsLog inGet started
Tessl Logo

sred-project-organizer

Take a list of projects and their related documentation, and organize them into the SRED format for submission.

53

Quality

60%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/sred-project-organizer/SKILL.md

The canonical home for this skill is sred-project-organizer in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured, complex workflow skill that clearly guides Claude through organizing SRED project documentation. Its strengths are the detailed step-by-step process with user review checkpoints and validation 'Ensure' blocks. Weaknesses include some verbosity in obvious instructions, confusing nested step numbering, and lack of error recovery guidance for tool interactions.

Suggestions

Rename the sub-steps within Step 5 to use a different naming convention (e.g., 5a, 5b, 5c) to avoid confusion with the top-level step numbering.

Add brief error handling guidance for common failure modes (e.g., Notion API failures, documents not matching expected format, inaccessible GitHub repos).

DimensionReasoningScore

Conciseness

The skill is fairly detailed and necessarily so given the complexity of the multi-step process, but there are areas of verbosity—e.g., the prerequisites section explains obvious things like 'if any of these can't be accessed, prompt the user to grant access,' and some ensure blocks repeat what's already implied. The repeated 'Ensure' blocks add some bulk but do serve as validation checkpoints.

3 / 5

Actionability

The skill provides concrete, step-by-step instructions with specific document formats, section names, word limits, and references to templates. However, it lacks executable code examples (e.g., specific MCP commands, gh CLI commands, or Notion API calls) and relies on Claude knowing how to interact with these tools. The guidance is specific enough to be actionable but not fully executable/copy-paste ready.

4 / 5

Workflow Clarity

The workflow is clearly sequenced with numbered steps and sub-steps, includes user review checkpoints at Steps 3, 5.3, and 5.8, and has 'Ensure' validation blocks throughout. However, there's no explicit error recovery/feedback loop (e.g., what to do if a Notion document can't be created, or if the Work Summary format doesn't match). The nested numbering (Step 5 containing Steps 1-8) could be confusing since it reuses 'Step' terminology.

4 / 5

Progressive Disclosure

The skill appropriately references external files (SRED.md, project-template.md) for detailed content rather than inlining it, and provides links to external resources. The structure is well-organized with clear sections. Minor gap: bundle files weren't provided so we can't verify the referenced paths exist, and the example link to a specific Notion document may not be accessible. The references section is clearly signaled at the bottom.

4 / 5

Total

15

/

20

Passed

Description

53%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 identifies a clear niche domain (SRED submissions) and provides a basic understanding of what the skill does, but it lacks specificity about the concrete actions involved and omits an explicit 'when to use' clause. Adding trigger terms like 'SR&ED', 'T661', and 'tax credit' along with a 'Use when...' statement would significantly improve skill selection accuracy.

Suggestions

Add a 'Use when...' clause with trigger terms like 'SR&ED', 'SRED', 'T661', 'scientific research tax credit', 'CRA submission'.

List specific concrete actions such as 'categorize eligible activities, calculate expenditures, generate T661 form sections, summarize technological uncertainties'.

Include the full name 'Scientific Research and Experimental Development' as a synonym alongside the acronym to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (SRED format/submission) and describes one concrete action (organize projects and documentation into SRED format), but lacks detail on specific sub-actions like categorizing expenditures, generating T661 forms, or identifying eligible activities.

3 / 5

Completeness

Has a clear 'what' (organize projects and documentation into SRED format for submission) but lacks an explicit 'when' clause. There is no 'Use when...' guidance to help Claude know when to select this skill.

3 / 5

Trigger Term Quality

Includes 'SRED' which is a key domain-specific term, and 'projects' and 'documentation' are relevant but generic. Missing natural synonyms like 'SR&ED', 'Scientific Research and Experimental Development', 'tax credit', 'CRA', or 'T661'.

3 / 5

Distinctiveness Conflict Risk

SRED is a fairly niche domain (Canadian tax credit program), which makes it reasonably distinct from other skills. However, it could potentially overlap with generic document formatting or tax preparation skills due to the lack of explicit boundaries.

4 / 5

Total

13

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.