skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
gasserane/personal-skills355 installs

mel-discipline

Use when producing any MEL/SRHR analytical deliverable (brief, evaluation design, indicator set, ToC, evidence review, data analysis) — especially under deadline pressure, on Opus/Sonnet/Haiku-class models, or when tempted to cite a source without opening it, skip a verification pass, or deliver in one draft. Also use when a specialist subagent prompt asks for "working discipline" or "five gates".

How do I install this agent skill?

npx skills add https://github.com/gasserane/personal-skills --skill mel-discipline
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill establishes a quality-control framework for analytical research, requiring strict citation verification and adversarial reasoning. No malicious behaviors, obfuscation, or unauthorized data access patterns were detected.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

What does this agent skill do?

MEL Working Discipline (Five Gates)

Overview

Rigour is a procedure, not a talent. This skill encodes the working discipline that top-tier models apply by default, so any model produces deliverables that survive a demanding peer review. Every analytical deliverable passes five gates, in order. Skipping a gate under deadline pressure is the failure mode this skill exists to prevent: a wrong citation in front of a Director costs more than the two minutes verification takes.

Violating the letter of a gate is violating its spirit.

Gate 1 — SCOPE before working

State in your first lines of work (not in the deliverable):

  1. The task in one sentence, and the decision it drives.
  2. Audience and register. Default: a working brief for colleagues who are not MEL specialists, 500–2500 words, with sources listed in an **Evidence base:** line at the end of each section rather than inside sentences. Use a publication register only when the task names a publication, journal article, or externally released report.
  3. Verification plan — one line: which facts, citations, or numbers you will check, and how.
  4. Pre-mortem — the single most likely way this deliverable misleads its named reader.

Gate 2 — EVIDENCE before reasoning

  • Materials you were given, and your team's own documents and knowledge sources, BEFORE web search.
  • Search-effort ladder: 1 search for a single fact; 3–5 for a medium task; 5–10 for deep research or comparison. State when you stop and why.
  • Citation rule: no source enters the deliverable unless you opened it this session. A citation you recall but did not open is either deleted or flagged ⚠️ URL unverified — confirm before publication. Partial recognition from training is not current knowledge.
  • Every kept citation: author + year + title + venue, plus a canonical link (publisher, institution, repository — never an aggregator as sole link).
  • Recency: check for a superseding edition; if citing an older source deliberately, say why in the standard form.

Gate 3 — REASON adversarially

  • Name the strongest objection to your own recommendation IN the deliverable, and answer it or concede it.
  • For causal or contribution claims: list the rival explanations and what the evidence says about each.
  • Agreement is a finding, not a reflex: if the obvious answer survives the objection, say why.

Gate 4 — VERIFY before declaring done

Run this checklist on the finished draft. Perform each check physically; never report a result you did not produce. In this skill's own wording test, a model reported "em-dash sweep: zero ✅" over a body containing five em-dashes. A claimed PASS without the performed check is itself a Gate 4 violation.

#CheckHow
1Every citation opened this session or flagged unverified — walked source by source through the Evidence base line, including frameworks, tools, and commissions named as design anchors; "well-known" grants no exemptionTrace each named source to the fetch/read that opened it, or attach the ⚠️ flag to that specific source. Observed failure (2026-07-07): a draft verified 1 of 4 Evidence-base sources and batch-passed the rest as canonical
2Em-dash sweep: zero U+2014 in body prose (data-gap separator ⚠️ Data gap: [what] — [why] — [action] exempt)Literal character search on the draft text (Grep/search tool when available; else re-read paragraph by paragraph hunting —). Rewrite each hit as a comma, colon, or two sentences
3BLUF: sentence 1 is the verdict or answerRead sentence 1
4Data gaps flagged in the standard format, never papered overScan for asserted-but-unsourced claims
5Numbers recomputed once from source, not carried forward on trustRecompute and state both values
6Register: length 500–2500 words for a working brief, citations in the Evidence base line rather than the running prose, acronyms spelled on first use, plain-English verbsScan

Gate 5 — REPORT faithfully

  • State what you verified and what you could not. An unverified item reported plainly beats a confident guess.
  • No hedging in the verdict; no overclaiming in the findings. "Will" for commitments, "should" for recommendations.
  • If the deliverable cannot reach standard with available information, say so with a data-gap flag instead of filling the gap with generic content.

Rationalizations — all mean STOP

ExcuseReality
"No time to verify, they need it in 20 minutes"Gate 4 takes 2 minutes. A fabricated citation in a management meeting costs the deliverable's credibility entirely.
"I remember this source, the link looks right"Plausible-but-unchecked is the signature failure. Open it or flag it.
"It's only a working brief, not a publication"Rigour is constant across tiers; only citation placement moves.
"The draft is clearly good, checks are overkill"The baseline test for this skill produced a good-looking brief with a likely-fabricated citation and four em-dashes. Good-looking is not verified.
"I'll note the caveats mentally"Unwritten caveats do not exist. Gate 5 puts them in the deliverable.
"I checked it while writing, no need to sweep again"The with-skill test asserted a clean em-dash sweep over five em-dashes. Checks done "while writing" are assertions. Perform the literal search on the finished draft.

Red flags — stop and run the gate you skipped

  • Pasting a URL you did not open this session.
  • Writing Author (year) without the source page in front of you.
  • Typing the final paragraph without having run the Gate 4 table.
  • A recommendation with no named objection anywhere in the deliverable.
  • Starting to draft before writing the verification plan line.
  • Reporting a Gate 4 ✅ for a check you did not physically perform on the finished draft.

Version

Team release v1.0 (2026-10-06). Adapted for colleagues from Ane Gasser's personal version of this skill: references to her own setup were replaced with generic equivalents; the five gates are unchanged.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/gasserane/personal-skills/mel-discipline">View mel-discipline on skillZs</a>