CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

handoff

Distills the current session's goal, state, remaining plan, key files, and gotchas into a copy-pasteable markdown handoff for a fresh agent or teammate, written to `.agent/{branch}/handoff.md` and the clipboard. Invoke with /handoff [focus phrase] [--brief].

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/authoring/handoff/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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, actionable skill body with an excellent workflow (explicit fallbacks, verified/assumed marking, and a definition-of-done checklist) and tight curation tables. The two real weaknesses are the dangling template reference — the file that defines the output format is not shipped — and some redundancy between the anti-patterns list and the Include/Exclude table.

Suggestions

Ship templates/handoff.template.md in the bundle or inline the template's section headings, since step 5 depends on a file that is currently missing.

Dedupe the Anti-patterns one-liners against the Include/Exclude table (raw-dump, secrets, and placeholder items each appear in both) to reclaim tokens.

Add a lightweight post-write validation loop to the workflow (e.g., re-read the written file and check the Definition of done items before reporting) to make the checklist a true feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's intelligence (no explanation of what git branches or clipboards are; curatorial rules like "would the next agent make a wrong move without it? If no, cut it" earn their tokens). It is not a 5 because the Anti-patterns one-liners partially restate the Include/Exclude table (raw dumps, secrets, TODO placeholders each appear twice).

4 / 5

Actionability

Concrete, executable guidance throughout: exact commands ("git rev-parse --abbrev-ref HEAD", "pbcopy < <path>"), explicit fallback chains for non-git repos and missing pbcopy, and a good/bad example pair with real file paths (src/cli.ts:parseArgs, tests/cli.test.ts). It falls short of 5 because the referenced template that defines the output structure (templates/handoff.template.md) is not in the bundle, leaving step 5 not fully executable as written.

4 / 5

Workflow Clarity

A clear 7-step numbered sequence with explicit validation checkpoints: scope stated before writing, fallback resolution reported per path, "Mark claims verified vs assumed", and a Definition of done checklist that validates the output (no secrets, no placeholders, path reported). This matches the top anchor's 'explicit validation steps; checklists' pattern rather than the anchor-4 'minor validation gaps'.

5 / 5

Progressive Disclosure

Sections are well-organized with headers and tables, but the body's single external reference — "[templates/handoff.template.md](./templates/handoff.template.md)" in step 5 — points to a file that does not exist in the bundle (no templates/, references/, scripts/, or assets/ directories are present). Navigation fails at the one place it is used, and the output template content lives nowhere accessible. Not a 2 because the in-body structure and section table still carry the skill; not a 4 because the sole reference is broken rather than merely unclear.

3 / 5

Total

16

/

20

Passed

Description

66%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 specific, distinct description that clearly states what the skill produces and where, with good natural trigger terms around "handoff" and "session". Its main weakness is the missing explicit "Use when..." guidance — the invocation syntax is not a trigger condition, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when ending a session, handing work to a teammate or fresh agent, or when the user asks for a handoff, briefing, or context transfer."

Include a few more natural synonyms users would say ("context", "briefing", "pick up where I left off") alongside "handoff" and "session".

DimensionReasoningScore

Specificity

Enumerates concrete content buckets ("goal, state, remaining plan, key files, and gotchas") and a specific output artifact ("written to .agent/{branch}/handoff.md and the clipboard"), matching the 'several specific actions; minor gaps' anchor. It is not a 5 because the capability boils down to one distilled 'distills... into a handoff' action rather than a comprehensive list of multiple distinct operations.

4 / 5

Completeness

The 'what' is clear and concrete (distills session into a markdown handoff written to a specific path and clipboard), but there is no 'Use when...' clause — "Invoke with /handoff [focus phrase] [--brief]" states invocation syntax, not when the skill is needed, so completeness is capped at 3 per the judging guidelines. It is above 2 because the 'what' is fully explicit rather than vague.

3 / 5

Trigger Term Quality

Natural terms users would say are present: "handoff", "session", "fresh agent", "teammate", plus the /handoff invocation phrase. Not a 5 because common synonyms like "context", "briefing", "continue where I left off", or "context transfer" are absent.

4 / 5

Distinctiveness Conflict Risk

"handoff" for "a fresh agent or teammate" with a distinct artifact path (.agent/{branch}/handoff.md) carves a clear niche with minor overlap risk against generic session-summary or planning skills. Not a 5 because terms like "plan" and "state" could mildly overlap with planning/briefing skills.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

13

/

16

Passed

Repository

mthines/agent-skills

Path

skills/authoring/handoff/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.