Personal productivity · Writing
reply-moves
/reply-moves
Use when drafting the words of a reply, after the stance is settled.
- Author
- TheDecipherist ↗
- Repository
- claude-packs ↗
- Licence
- MIT
- Last repository change
- 11.11.2026
Assessment and security
82/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability21 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
Deprecation
No signals detected. Repository changed on 11.11.2026, without references to retired models or APIs.
Licence
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when drafting the words of a reply, after the stance is settled.
Original author description
Use when drafting the words of a reply, after the stance is settled.
How it works
SKILL.md has no level-two headings · 37 lines, 314 words
SKILL.md preview
---
name: reply-moves
description: Use when drafting the words of a reply, after the stance is settled.
---
# Reply moves by situation
All replies: no preamble, conclusion first. (Posts are different: `post-voice`.)
- **Wrong AND smug:** soft-flex opener, receipt, flat correction. "I'm
sorry but I think you need to read the docs again [link]. Skills are
injected at session start..."
- **Wrong but polite:** skip the jab, open with the source or flat fact,
calm. Calm is not agreeing; the false premise still gets corrected.
- **Polite AND sharp but framing wrong (the dangerous one):** acknowledge
nothing false. Correction stated flat, one concrete consequence, stop.
- **True fact, false conclusion:** agree with the true fact plainly (that's
not a concession), then refute the conclusion hard. Two reusable moves:
the "it would already be baked in" move (if saying X were enough, Claude
would already do X by default), and SHOW the specific instead of
asserting it: give the actual list of concrete rules, and verify every
item is airtight; one vague bullet undercuts the whole point.
- **Confidently misframing:** flat correction, conclusion first, one
consequence, stop.
- **Genuine question (lost, not challenging):** straight into plain
language, lead with an analogy, end on a crisp one-line distinction
("skills help, hooks enforce").
- **Disagreeing with an upvoted crowd belief:** open hard, stack flat
declarative reasons, end with the fix. "I'm sorry but you are way off...
Just give it a detailed description of what you want built and how."
- **Praise:** take it cleanly. "Thanks brother. Appreciate it." No
deflecting, no over-thanking.
**Target register for replies (the author's own words, study it):**
> Hooks are the only thing that can cover you. There is no enforcement in
> a skill or in Claude.md for that matter. Hooks are the only thing that
> can stop Claude from reading, writing or piping a curl command through
> shell to steal all your personal information.
Conclusion first. Flat declaratives. Threat named plainly. Then it stops.
Versions
The database has no other skills named reply-moves.
Database snapshot: 13.11.2026 · package version 8075928f1f5c (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 96reply-stance
Use when about to draft any reply to a comment, a review or a thread, or when asked whether to agree with what someone said. - 92pr
Use when writing a PR body. - 100write-plan
Write an implementation plan. Use when the behavior is settled and how to build or fix it is open — a pinned cause, settled spec, hunt finding, or review comment. Not for deciding the behavior (write-specs) or multi-session work (frontier). - 86log-reply
Record an employer's reply (rejection, interview, offer, anything) in applications.md and update the summary line. Use when they type /log-reply or mention hearing back from an employer. - 100shape
Use when a feature has settled intent and codebase facts but multiple viable implementation approaches remain.