CtrlK
BlogDocsLog inGet started
Tessl Logo

deadline-radar

Unified timeline of all deadlines from emails, calendar, and vault. Groups by urgency (overdue, critical 48h, upcoming 7d, distant) with alert levels. Triggers: EN: "deadline radar", "what are my deadlines", "this week's deadlines", "upcoming deadlines". IT: "scadenze", "radar scadenze", "le mie scadenze", "scadenze della settimana". FR: "échéances", "radar des échéances". ES: "fechas límite", "radar de plazos". DE: "Fristen-Radar", "meine Fristen". PT: "radar de prazos", "meus prazos".

60

Quality

70%

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 ./tests/regression/snapshot/.claude/skills/deadline-radar/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 body is actionable and reasonably structured with executable commands and a useful template, but it repeats scan instructions, lacks validation checkpoints for a batch aggregation task, and keeps reference material inline rather than progressively disclosed. Tightening duplication and adding cross-source validation would raise the weakest dimensions.

Suggestions

De-duplicate the Hey/GWS/MCP scan instructions between the Security and Procedure sections so each source's commands appear once.

Add an explicit validation step (e.g. dedupe deadlines across sources and confirm none were missed before generating the timeline) to lift workflow clarity above the batch-operation cap.

Move the inter-agent coordination protocol detail into a referenced file and keep only a brief inline pointer, with the reference clearly signaled where it is first needed.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands, but sections repeat the same Hey/GWS/MCP scan instructions (Procedure step 1 vs Security section) and the inter-agent coordination block adds length that assumes little about what Claude already knows.

3 / 5

Actionability

Concrete executable commands are given throughout (gws gmail users messages list, hey box imbox --json, gws calendar events list) with a copy-paste-ready template; minor gaps include unspecified exact Gmail query syntax and placeholder-heavy report blocks.

4 / 5

Workflow Clarity

A clear five-step scan sequence exists, but for a batch read-and-report operation there are no validation checkpoints (e.g. confirming scan coverage, deduping cross-source deadlines, verifying the merged timeline), so per the destructive/batch guidance the score is capped at 3.

3 / 5

Progressive Disclosure

Well-organized with clear section headers, but it is a single monolithic SKILL.md that inlines substantial reference-style material (agent-orchestration protocol, registry pointers) rather than splitting it out; references to .claude/references/* are buried at the end without inline signaling.

3 / 5

Total

13

/

20

Passed

Description

82%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 is specific, trigger-rich, and distinct, with concrete actions and broad natural-language coverage across six languages. The main gap is the absence of a clean standalone 'Use when...' clause, which keeps completeness just below the top anchor.

Suggestions

Add an explicit 'Use when ...' sentence separate from the trigger list to make the invocation condition unambiguous.

Tighten the action list so each concrete capability (scan, group, alert, report) reads as a distinct verb phrase.

DimensionReasoningScore

Specificity

Lists several concrete actions (scan emails/calendar/vault, group by urgency, alert levels, trigger phrases) but the action set is narrow around a single aggregation task, leaving minor coverage gaps.

4 / 5

Completeness

Clearly answers 'what' (unified deadline timeline grouped by urgency) and provides explicit trigger phrases for 'when', but the 'when' framing leans on trigger keywords rather than a distinct 'Use when...' clause, leaving it slightly less explicit than ideal.

4 / 5

Trigger Term Quality

Comprehensive natural trigger phrases across six languages ('deadline radar', 'what are my deadlines', 'scadenze della settimana', etc.) covering the core terms users would actually say.

5 / 5

Distinctiveness Conflict Risk

The deadline-aggregation niche is specific and the multi-language trigger set is distinctive, making overlap with general email or calendar skills minimal.

5 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
gnekt/My-Brain-Is-Full-Crew
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.