Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kjendrzyca-tally
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/tally
What's inside
- Skill name
tally- Description
- Create and edit Tally.so forms and read responses.
- License
- MIT
- Instructions
- 82 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- mcporter.json
- connection.md · references/
- mcporter-daemon.md · references/
- mcporter-discovery.md · references/
SKILL.md (first lines)
# 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](references/connection.md) for setup.
## Discover only what you need
1. Read compact tool signatures:
```bash
mcporter --config "$TALLY_MCP_CONFIG" list tally --brief --no-oauth
```
2. Pick the exact tool name from that output, then inspect only its schema.
For large tools (`create_blocks`, `configure_blocks`, `update_settings`), use
[filtered discovery](references/mcporter-discovery.md) to read only the needed
block types, operations, or settings. For small tools:
```bash
mcporter --config "$TALLY_MCP_CONFIG" list tally.TOOL_NAME --schema --no-oauth
```
3. Call the tool with arguments matching its current schema:
```bash
mcporter --config "$TALLY_MCP_CONFIG" call tally.TOOL_NAME --args '{"ARGUMENT":"VALUE"}' --output json --no-oauth
```
`TOOL_NAME`, `ARGUMENT`, and `VALUE` are placeholders. Do not guess names or
reuse arguments from a different tool. For large payloads, use a
local JSON file and shell-quote its contents: `--args "$(cat /absolute/path/arguments.json)"`.
If authentication is missing, follow [connection.md](references/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](references/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_form` or `load_form`. Edit through the returned ledger
and targeted MCP tools. These changes remain in memory until `save_form`.
- Create the form the user requested. Use `DRAFT` unless 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.status` explicitly: its current default is `PUBLISHED`.
After the first save, always pass the saved `formId` on 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_blocks` currently makes questions required. Use `configure_blocks`
to make requested fields optional, then verify the ledger.
- `create_blocks` may strip the final parenthesized phrase from a question title.
If the intended title ends with `(...)`, restore the full title using
`update_text` after creation. Verify it after saving and reloading the form.
- Before saving, call `list_blocks` and compare the working content with the
request. After saving, reload the saved form and check its content; verify
status through saved metadata or `list_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.From kjendrzyca/public-skills, MIT.
More from kjendrzyca/public-skills
- 0.582score
one-by-one
kjendrzyca
Ask the user a list of questions one at a time, letting each answer reshape the rest.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
battery-stats
kjendrzyca
Check macOS laptop battery telemetry, current power drain, average watt usage, battery health, cycle count, and recent real-world battery runtime from local…
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
video-analysis
kjendrzyca
Analyze local video or audio files with ffmpeg/ffprobe, Parakeet MLX or Whisper transcription, contact sheets, checkpoint frames, and timestamped issue notes.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
coding-audit-assumptions
kjendrzyca
Think out of the box about a software problem or planned solution by questioning the assumptions that make it hard, then propose a different way to solve it -…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
coding-consult-design
kjendrzyca
Run a structured, repository-grounded consultation with Codex CLI or Claude Code on a non-trivial software problem, proposed fix, design decision…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ask-claude
kjendrzyca
Delegate focused analysis, code review, execution-plan review, or second-opinion work to Claude Code through non-interactive `claude -p`.
SkillBFreshness: B★ 1Claude Code +9 - 0.546score
record-macos-window
kjendrzyca
Record a single macOS window as silent video with a verified 60 fps export.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
coding-explain-problem
kjendrzyca
Explain coding problems, code behavior, review findings, architecture, or proposed changes in plain language.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
ntd-tasks
kjendrzyca
Fetch and manage NoThinkDo tasks.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
handoff
kjendrzyca
Compact the current conversation into a handoff document for another agent to continue from.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 21, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kjendrzyca/public-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kjendrzyca
- 0.582score
one-by-one
kjendrzyca
Ask the user a list of questions one at a time, letting each answer reshape the rest.
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
battery-stats
kjendrzyca
Check macOS laptop battery telemetry, current power drain, average watt usage, battery health, cycle count, and recent real-world battery runtime from local…
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
video-analysis
kjendrzyca
Analyze local video or audio files with ffmpeg/ffprobe, Parakeet MLX or Whisper transcription, contact sheets, checkpoint frames, and timestamped issue notes.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
coding-audit-assumptions
kjendrzyca
Think out of the box about a software problem or planned solution by questioning the assumptions that make it hard, then propose a different way to solve it -…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
coding-consult-design
kjendrzyca
Run a structured, repository-grounded consultation with Codex CLI or Claude Code on a non-trivial software problem, proposed fix, design decision…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ask-claude
kjendrzyca
Delegate focused analysis, code review, execution-plan review, or second-opinion work to Claude Code through non-interactive `claude -p`.
SkillBFreshness: B★ 1Claude Code +9
Cite this page
tally skill. Agent Mart. https://agentmart.dev/skills/kjendrzyca-tally (last updated 2026-10-24)