CtrlK
BlogDocsLog inGet started
Tessl Logo

x-backlog

Use when the user wants to capture a brainstormed idea, feature, or solution into a durable backlog/spec doc under docs/backlog — a human-facing reference that combines context, chosen solution, key decisions (ADR-lite), scope, acceptance criteria, and optional feature/integration/contract/use-case/handoff modules. Drafts the whole doc autonomously from the current conversation and persists docs/backlog/<slug>.md; asks the user only when blocked or a decision genuinely needs their input. NOT a low-level implementation plan (that is superpowers:writing-plans / x-do).

64

Quality

78%

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/x-backlog/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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-sequenced, actionable instruction skill with concrete tool signatures and clear validation checkpoints, undermined by verbosity in the handoff and memory-reflex sections and a broken mandatory reference (gotchas.md is required but not shipped in the bundle). Tightening the inlined detail and providing the missing file would lift the weakest dimensions.

Suggestions

Ship the missing gotchas.md (referenced as a mandatory bootstrap load) or remove the 'load gotchas.md' requirement and inline only the essential gotchas.

Move the dense [W] handoff state matrix and the Memory Reflex gating rules into a reference file (e.g. references/handoff.md) and keep SKILL.md as a concise overview, fixing both conciseness and progressive_disclosure.

Add a one-line retry/escalation note to the step 6 self-review (e.g. 'if a contradiction spans multiple sections, re-run step 4 for the affected sections') so the validation step has a real feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient (compact anti-triggers table, numbered steps, exact tool signatures), but several sections are padded — notably the [W] handoff bullet ('Two doc states carry cleanly... The third state does not... On a bare [W] with an untracked doc, also revert the step-5 README row...') and the Memory Reflex gating, which is re-explained in Bootstrap and again in steps 2 and 6. Matches the score-3 anchor (mostly efficient, some unnecessary explanation that could be tightened); not 4 because the padding is noticeable rather than minor.

3 / 5

Actionability

Concrete, executable guidance throughout: exact file path docs/backlog/<slug>.md, exact MCP call signatures (mcp__basic-memory__search_notes({ query:..., page_size:5 }), mcp__basic-memory__write_note({...})), commit message format docs(backlog): add <slug>, and specific handoff dispatch commands. Per scoring_notes, absence of code in this instruction-only skill is not penalized. Matches the score-4 anchor; not 5 because some conditional guidance (the [W] state matrix) leaves execution ambiguous rather than copy-paste ready.

4 / 5

Workflow Clarity

Six clearly sequenced steps with explicit checkpoints: step 3 blocker checkpoint ('Ask the user only when one of these blockers holds'), step 6 fresh-eyes self-review pass, and [ ] checklists for memory beats. Matches the score-4 anchor (clear sequence, most checkpoints present, minor validation gaps); not 5 because the self-review is explicitly single-pass ('No re-review loop — fix and move on'), so the error-recovery feedback loop is incomplete.

4 / 5

Progressive Disclosure

Structure is mostly one-level-deep (SKILL.md overview → references/template.md, gotchas.md), but gotchas.md is referenced as a MANDATORY bootstrap load ('Before walking, load: ... gotchas.md') and again under 'Gotchas → See gotchas.md' yet is absent from the bundle (only references/template.md exists). Additionally, substantial operational detail (the Memory Reflex gating rules and the [W] handoff state matrix) is inlined in SKILL.md rather than moved to a reference. Matches the score-3 anchor (some structure, references present but one is broken/missing, content that could be separate is inline); not 4 because a missing mandatory reference is more than a minor organization gap.

3 / 5

Total

14

/

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: it states a clear niche, concrete capabilities, an explicit 'Use when...' trigger, and active disambiguation against sibling skills. The only meaningful gap is trigger-term breadth — a few natural synonyms and file extensions are missing.

Suggestions

Add a few natural synonyms/file extensions to the trigger clause (e.g. 'design doc', 'requirements', 'spec', '.md') to broaden natural-language match coverage.

Consider adding one or two short example trigger phrases users would actually type ('add this to the backlog', 'write up this feature as a spec').

DimensionReasoningScore

Specificity

Names the domain (durable backlog/spec doc) and multiple concrete actions: 'capture a brainstormed idea... into a durable backlog/spec doc', 'combines context, chosen solution, key decisions (ADR-lite), scope, acceptance criteria, and optional...modules', 'Drafts the whole doc autonomously', 'persists docs/backlog/<slug>.md', 'asks the user only when blocked'. Coverage is comprehensive across the doc's components and behaviors, matching the score-5 anchor; not 4 because no meaningful action gap remains.

5 / 5

Completeness

Explicitly answers both: what ('combines context, chosen solution, key decisions... scope, acceptance criteria... Drafts the whole doc autonomously... persists docs/backlog/<slug>.md') and when ('Use when the user wants to capture a brainstormed idea, feature, or solution into a durable backlog/spec doc'). Matches the score-5 anchor with concrete trigger phrases; not 4 because 'when' is explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Natural trigger phrases are present — 'Use when the user wants to capture a brainstormed idea, feature, or solution', 'backlog/spec doc' — which a user would plausibly say. Not 5 because synonym/file-extension coverage is incomplete (no '.md', 'spec', 'requirements', 'design doc' variants) and the term set, while good, is not exhaustive; not 3 because coverage is clearly good rather than partial.

4 / 5

Distinctiveness Conflict Risk

Clear niche (spec/backlog crystallization between brainstorming and implementation) with active disambiguation: 'NOT a low-level implementation plan (that is superpowers:writing-plans / x-do)'. Minimal conflict risk; matches the score-5 anchor; not 4 because overlap risk is explicitly countered rather than merely minor.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
quangtran88/x-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.