agentsclimarketplace

Consult consistency lint

Skill Timelnapp/skills/skills/consulting-os/consult-consistency-lint

6 SKILLs to improve Claude Code memory, derived from Timeln's second brain capability to remember everything.

Install
npx -y skills add Timelnapp/skills --skill consult-consistency-lint

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Trigger on "consult lint", "consistency pass", "diagram vs narrative", "broken promises across docs", "cross-artifact check", "scope drift lint". Read-only diff across frame, arc, gates, acceptance, commercial, architecture artifact. NOT rewriting copy (use consult-package), NOT drawing diagrams (use arch-diagrams).

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.7 KB, 557 tokens by cl100k_base, as published. Nobody here has run it

Consult Consistency Lint -- Cross-Artifact Diff

Flag inconsistencies: text vs diagram, missing acceptance for a phase, duplicated/conflicting scope, option drift.

Inputs

InputRequired
Latest consult-frame, consult-arc, consult-gates, consult-acceptance, consult-commercialyes
Architecture artifact (Mermaid, draw.io path, image, or bullet list from arch-diagrams)optional

Workflow

  1. Phase coverage -- every phase in gates has exactly one acceptance row; flag orphans either direction.
  2. Option alignment -- MVP/Pilot/Full names and definitions match across arc, gates, commercial; flag renamed or missing options.
  3. Scope strings -- in/out scope in frame must not reappear as promised deliverables unless explicitly in acceptance; flag contradictions.
  4. Decision thread -- arc "thread" sentence must match frame primary decision; flag mismatch.
  5. Diagram vs text -- for each box/layer in the architecture artifact, map to a noun in arc or acceptance; unmapped diagram elements or unmapped promises in text get FINDING.
  6. Commercial vs gates -- durations/options must reference the same phased path; flag phases with no timebox or timebox with no phase.
  7. Placeholder scan -- TBD, TODO, unknown -- confirm, lorem, angle brackets; list file/section if known from paste titles.

Output -- exactly this shape

## Lint -- <client or "TBD"> -- <YYYY-MM-DD>

**Summary**
- Critical: <n>
- Warning: <n>

**Findings**
| ID | Severity | Where | Issue | Suggested fix |
|---|---|---|---|---|
| L1 | critical | ... | ... | ... |

**Clean checks passed**
- <bullet list of checks that passed>

Severity: critical = would embarrass in client readout or breaks contract intent; warning = clarity or internal consistency.

Rules

  • Do not invent architecture elements -- if no diagram supplied, skip diagram checks and note skipped -- no architecture artifact.
  • If an input artifact is missing, list as missing -- <skill name> and skip dependent checks.
  • Suggested fix is one line each; no full rewrites.

Common failure modes

MistakeFix
Nitpicking tone differencesOnly flag semantic or commitment drift
Auto-resolving conflictsReport -- let owner choose
Missing diagram treated as passMust emit skipped line

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most quality gates skills give in 557 tokens

Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07

  • read the output and check the exit codein 54 of 1195, across 14 files
  • verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
  • identify the verification command proving the claimin 51 of 1195, across 12 files
  • run the full verification commandin 50 of 1195, across 11 files
  • verify output confirms the claimin 49 of 1195, across 12 files
  • check version control diff after agent delegationin 46 of 1195, across 6 files
  • state claim with evidencein 44 of 1195, across 4 files
  • run the test suitein 33 of 1195, across 26 files
  • keep state in memory by defaultin 27 of 1195, across 6 files
  • make prototype runnable with one commandin 26 of 1195, across 5 files
  • produce a verification reportin 25 of 1195, across 14 files
  • detect the package manager from lockfilesin 24 of 1195, across 5 files

Said here and by no other author read

  • check phase coverage between gates and acceptance
  • flag orphaned phases in either direction
  • verify option names and definitions match across artifacts
  • check scope strings for contradictions
  • verify decision thread sentences match frame primary decision
  • map architecture artifact boxes to arc or acceptance nouns

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.