tally
Skill1 starsChanged 3 months agoMITView on GitHub
Create and edit Tally.so forms and read responses.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- bingelp/skillstheir own version, first seen Oct 20, 2026
- LiozShor/claude-code-skillstheir own version, first seen Aug 19, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- LiozShor/claude-code-skills★ 2same name
- bingelp/skills★ 0same 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ask-claudeSkill
- battery-statsSkill
- coding-audit-assumptionsSkill
- coding-consult-designSkill
- coding-explain-problemSkill
- handoffSkill
- ntd-tasksSkill
- one-by-oneSkill
- record-macos-windowSkill
- show-meSkill
- video-analysisSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 5 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Use the official Tally MCP server through MCPorter.
- Distinctive: line 18
Read compact tool signatures:
- Distinctive: line 33
Call the tool with arguments matching its current schema:
- Distinctive: line 43
If authentication is missing, follow connection.md.
- Distinctive: line 44
Do not dump all schemas or load all reference pages.
- Very specific: line 49
Before create_new_form, load_form, or any operation on the working form, read mcporter-daemon.md and acquire its session lock.
- Very specific: line 53
Start with create_new_form or load_form.
- Very specific: line 55
Create the form the user requested.
- Very specific: line 58
Always pass save_form.status explicitly: its current default is PUBLISHED.
- Very specific: line 59
After the first save, always pass the saved formId on subsequent saves.
- Distinctive: line 60
Before editing, load the target form and retain its existing IDs.
- Very specific: line 65
If the intended title ends with (...), restore the full title using update_text after creation.
- Very specific: line 67
Before saving, call list_blocks and compare the working content with the request.
- Very specific: line 84
Read them on demand through MCPorter.
≈ “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
Tally
Use the official Tally MCP server through MCPorter. Resolve mcporter.json
relative to this SKILL.md, and set TALLY_MCP_CONFIG to that resolved absolute
path in each shell invocation (or export it in a persistent shell). Do not infer
it from the working directory. Examples below assume this variable is set.
The bundled config uses OAuth, keeps the connection alive, and disables imports
from other MCP clients. See connection.md for setup.
Discover only what you need
Read compact tool signatures:
mcporter --config "$TALLY_MCP_CONFIG" list tally --brief --no-oauthPick the exact tool name from that output, then inspect only its schema. For large tools (
create_blocks,configure_blocks,update_settings), use filtered discovery to read only the needed block types, operations, or settings. For small tools:mcporter --config "$TALLY_MCP_CONFIG" list tally.TOOL_NAME --schema --no-oauthCall the tool with arguments matching its current schema:
mcporter --config "$TALLY_MCP_CONFIG" call tally.TOOL_NAME --args '{"ARGUMENT":"VALUE"}' --output json --no-oauthTOOL_NAME,ARGUMENT, andVALUEare placeholders. Do not guess names or reuse arguments from a different tool. For large payloads, use a local JSON file and shell-quote its contents:--args "$(cat /absolute/path/arguments.json)".
If authentication is missing, follow connection.md. Do not dump all schemas or load all reference pages. MCP tools may themselves return usage instructions; follow those for the chosen operation.
Forms
- Before
create_new_form,load_form, or any operation on the working form, read mcporter-daemon.md and acquire its session lock. The keep-alive connection is shared by agents and holds one working form. Hold the lock through editing, saving, and verification; never interleave forms. - Start with
create_new_formorload_form. Edit through the returned ledger and targeted MCP tools. These changes remain in memory untilsave_form. - Create the form the user requested. Use
DRAFTunless publishing was requested; preserve an existing form's status unless the task changes it. If a tool cannot express the requested status, explain that before writing. - Always pass
save_form.statusexplicitly: its current default isPUBLISHED. After the first save, always pass the savedformIdon subsequent saves. - Before editing, load the target form and retain its existing IDs. Use UUIDs from the returned ledger; MCP creation tools generate new IDs.
create_blockscurrently makes questions required. Useconfigure_blocksto make requested fields optional, then verify the ledger.create_blocksmay strip the final parenthesized phrase from a question title. If the intended title ends with(...), restore the full title usingupdate_textafter creation. Verify it after saving and reloading the form.- Before saving, call
list_blocksand compare the working content with the request. After saving, reload the saved form and check its content; verify status through saved metadata orlist_forms. Do not reload during unsaved editing, because loading replaces the working form. Report its ID/link and whether it is draft or published. If a save times out, inspect stored state before retrying; do not blindly create a duplicate.
Responses
Inspect fetch_submissions for response retrieval or fetch_insights for
aggregate analytics. Filter to the requested form, period, and completion state;
follow pagination when the task needs the complete set. Report the scope and
number of responses covered. Keep answers out of the skill and committed fixtures.
Further details
Tool descriptions and live schemas define the supported operations and arguments.
Read them on demand through MCPorter. If they leave a product question unanswered,
inspect and use Tally's search_documentation tool. Report missing capabilities;
do not invent tools or silently switch to another interface.
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.

