title-shotgun
Skill17 starsChanged 3 months agoMITView on GitHub
Generates 8-12 title candidates across forms (declarative, question, colon, anomaly, mechanism), scores hook x precision x searchability, and pairs the winner with the abstract framing. Use late in writing when the user asks for title ideas or a better title.
In this repository38 other files it gives its agents.
- abstract-shotgunSkill
- analyzeSkill
- archiveSkill
- carefulSkill
- coauthor-reviewSkill
- codebookSkill
- cover-letterSkill
- data-acquireSkill
- data-cleanSkill
- design-researchSkill
- draft-sectionSkill
- freezeSkill
- guardSkill
- hypothesis-designSkill
- idea-shotgunSkill
- identification-reviewSkill
- journal-fitSkill
- learnSkill
- lit-mapSkill
- llm-checklistSkill
- mstack-initSkill
- mstack-upgradeSkill
- paper-statusSkill
- pdf-ingestSkill
- power-analysisSkill
- preregisterSkill
- r-and-rSkill
- referee-mockSkill
- research-questionSkill
- results-auditSkill
- retroSkill
- robustnessSkill
- scope-challengeSkill
- submission-packSkill
- survey-buildSkill
- theory-buildSkill
- unfreezeSkill
- vizSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Stage: write · Voice: writer
- Very specific: line 15
After /mstack:abstract-shotgun settles a framing.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/mstack:title-shotgun
Stage: write · Voice: writer
After /mstack:abstract-shotgun settles a framing; editors and search engines read title and abstract together, so pair them deliberately.
Procedure
- Load
paper/sections/abstract.texand.mstack/config.yaml(journals favor different title styles). Generate 8–12 candidates across forms:
Form Example Declarative "Trade Exposure Raises Protectionist Voting" Question "Does Trade Exposure Raise Protectionist Voting?" Colon (general: specific) "Threats to Trade: How Import Competition Reshapes Voting in Three Democracies" Anomaly "When the Losers Win: Compensation and Backlash in the Globalization Era" Mechanism "Compensation Without Trust: Why Aid to the Trade-Exposed Doesn't Move Votes" Quote "'Bring the Jobs Back': Industrial Decline and Electoral Realignment" Number-led "Three Decades of Trade Shocks and the New Politics of Protection" Single noun phrase "The Protectionist Turn" - Score 1–5 on hook (would a reader stop scrolling?), precision (does it convey the claim?), searchability (would the right reader find it by keyword?).
- Filter: drop any title with a 1 in any dimension; rank by
hook × precision × searchability; surface the top 3. - Recommend one, paired with the abstract framing: finding-first pairs with declarative, puzzle-first with a question or anomaly title.
- Save to
.mstack/title-shotgun-<YYYY-MM-DD>.md.
Outputs
.mstack/title-shotgun-<date>.md— candidates, scores, recommendation.- Summary block: top 3 with scores + recommendation.
Anti-patterns
- Clever but vague. Two readings to parse fails hook and precision.
- Variables in the title. "Effect of X on Y in Z" is a placeholder.
- Subtitle longer than title. Reverse the colon.
Next
/mstack:journal-fit to confirm the pair suits the target journal's style.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

