help-me
Skill2 starsChanged 37 days agoMITView on GitHub
Decide how to approach a task. Given "I need to do X", recommend the skills and development patterns to use, in order.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- lalulali/vespyrtheir own version, first seen Nov 6, 2026
- joris887/exosuittheir own version, first seen Aug 20, 2026
- hereinthehive/kickstarttheir own version, first seen May 27, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- lalulali/vespyr★ 11same name
- joris887/exosuit★ 9same name
- hereinthehive/kickstart★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
- setup-fassi-skillsSkill
- write-commitSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
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 15
Available skills: every skill this session already lists, by its name and description.
- Very specific: line 35
When a registry workflow fits, recommend that workflow whole and respect workflow_rule.
- Distinctive: line 39
Keep it to what the user can act on:
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
The user has a task and wants to know how to approach it, not to have it done. Answer with one recommended path made of skills and development patterns. Start the work only when they say so.
1. Get the task
The task is the argument passed to this skill. With no argument, ask in one line what they need to do.
2. Gather the candidates
- Available skills: every skill this session already lists, by its name and description.
- Registry skills: the
skills,workflows,workflow_ruleandtoolsof the manifest, at../setup-fassi-skills/manifest.jsonrelative to this file, or else at https://raw.githubusercontent.com/sh4wty1/fassi-skills/main/skills/setup-fassi-skills/manifest.json. When neither is reachable, carry on with the available skills alone and say so. - The project:
AGENTS.md/CLAUDE.mdand the code the task touches, read only as far as needed to judge the task's size and what conventions already exist.
3. Size the task
Settle these from the task and the project. Ask the user only for what you could not settle and that would change the recommendation, in at most two questions.
| Question | Points to |
| Is what to build still open? | Interview and spec first (grilling, spec skills) before any code. |
| Is the behaviour clear and testable? | Test-first: one failing test, make it pass, refactor. |
| Is it something broken or slow? | Reproduce it first, then diagnose; no fix before a reproduction. |
| Is the doubt about how it should feel or look? | A throwaway prototype, discarded after it answers the question. |
| Does it span several modules or sessions? | A spec cut into tickets, one ticket per session. |
| Does it change a module's shape or interface? | Design the interface first, then move callers in small steps. |
| Is it hard to undo (migration, cutover, public API)? | Smallest reversible slice first, with a way back written down. |
| Is it a finding from an audit or report (SEO, accessibility, performance, security)? | The registry skill for that area, pointed at the finding alone. |
| Is it small, clear and local? | No process: just do it, then review the diff. |
When a registry workflow fits, recommend that workflow whole and respect workflow_rule.
4. Answer
Keep it to what the user can act on:
- The path: numbered steps in the order to do them. Each step names a skill (as the command to type) or a pattern, with one line on why it fits this task. For a registry skill, add what it does when run and what it needs (an MCP, a CLI, a token), since the user may never have used it.
- Not installed: mark any recommended skill that is not available in this session, and point to
/setup-fassi-skillsto install it. - The alternative: one other path and the condition under which it would be the better choice.
- What to skip: process that would be overkill for this task, in one line.
Recommend one path. When no skill fits a step, name the pattern alone rather than stretching a skill to cover it.
End by offering to start on step 1.
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.