Actualize
NeoLabHQ/context-engineering-kit
Reconcile the project's FPF state with recent repository changes
Work out what actually happened to a CALL-E call by reading the call task, its attempts and its event stream together, and say which field each conclusion came from.
MITAuto-check passed
Install Call State Reconciler
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents call-state-reconciler --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/call-state-reconciler .claude/skills/call-state-reconciler && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "call-state-reconciler" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-state-reconciler into .claude/skills/call-state-reconciler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-state-reconciler", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-state-reconcilerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents call-state-reconciler --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/call-state-reconciler .agents/skills/call-state-reconciler && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "call-state-reconciler" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-state-reconciler into .agents/skills/call-state-reconciler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-state-reconciler", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents call-state-reconciler --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/call-state-reconciler .cursor/skills/call-state-reconciler && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "call-state-reconciler" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-state-reconciler into .cursor/skills/call-state-reconciler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-state-reconciler", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/CALLE-AI/awesome-phone-call-agents.git --path skills/call-state-reconciler--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents call-state-reconciler --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/call-state-reconciler .gemini/skills/call-state-reconciler && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "call-state-reconciler" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-state-reconciler into .gemini/skills/call-state-reconciler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-state-reconciler", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install CALLE-AI/awesome-phone-call-agents call-state-reconcilerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/call-state-reconciler .github/skills/call-state-reconciler && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "call-state-reconciler" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-state-reconciler into .github/skills/call-state-reconciler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-state-reconciler", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CALLE-AI/awesome-phone-call-agents call-state-reconciler --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/call-state-reconciler .opencode/skills/call-state-reconciler && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "call-state-reconciler" agent skill from https://github.com/CALLE-AI/awesome-phone-call-agents/tree/main/skills/call-state-reconciler into .opencode/skills/call-state-reconciler/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "call-state-reconciler", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
call-state-reconciler- GitHub stars
- 107
- Token cost
- ~1.4k tokens
- SKILL.md length
- 820 words
- Files
- 5 (incl. references)
- Skills in repo
- 101
- Repo updated
- First seen
- Licence
- MIT
At a glance
Work out what actually happened to a CALL-E call by reading the call task, its attempts and its event stream together, and say which field each conclusion came from.
- A workflow acts on a call result
- SKILL.md covers When to use it, The one field that changes…, The four things it reconciles and Read the event stream, not the…, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- A call will not settle
What it does
Call State Reconciler is an agent skill from CALLE-AI/awesome-phone-call-agents. Work out what actually happened to a CALL-E call by reading the call task, its attempts and its event stream together, and say which field each conclusion came from. Use when a workflow acts on a call result, when a call will not settle, or when the platform's own signals disagree with each other.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/examples.md`, `references/observed-shapes.md` and `references/reading-a-call.md`).
The repository describes itself as: Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents. The licence is MIT.
When your agent uses it
- A workflow acts on a call result
- A call will not settle
- The platforms own signals disagree with each other
Example prompts
- “/call-state-reconciler”
What it can do on your machine
Read from SKILL.md and the folder at commit 38d4118. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Call State Reconciler loads about 1.4k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 820 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 820 words, ~1,366 tokens.
Download SKILL.mdSave it as
.claude/skills/call-state-reconciler/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- call-state-reconciler
- description
- Work out what actually happened to a CALL-E call by reading the call task, its attempts and its event stream together, and say which field each conclusion came from. Use when a workflow acts on a call result, when a call will not settle, or when the platform's own signals disagree with each other.
- license
- MIT
Call State Reconciler
A finished call hands you a status word, a task_completed boolean and a
confidence score. Three answers jammed into a shape that looks like one, and
the one everybody branches on is task_completed.
It comes back true for a voicemail box. The recording picks up, the agent
asks its question into the tone, and the call ends completed with a
schema-valid result and a high score. Nothing in that payload is a lie. There
is simply no field in it that says a person was ever on the line.
This skill covers reading a call properly: how it ended, whether the job got done, and whether the answer came from anybody speaking. Three separate questions, answered separately, each one carrying the field it was read from.
When to use it
Use it before a call result moves anything in a system of record. Booking, dispatching, charging, closing a ticket, marking a lead dead.
Use it when a call will not settle, or when you are looking at a batch of calls and need to know which ones need a person today.
Use it when two signals disagree: the call task says one thing and its recipient says another, or the attempt timing does not match the event stream.
Do not use it on a call nobody acts on automatically. A call that produces a note for a human to read has no branch to get wrong, and this is overhead.
The one field that changes everything
The Calls API carries no answered-by field. The calls guide says so directly and tells you to define the classification yourself in a per-recipient result schema:
{
"type": "object",
"required": ["answered_by"],
"properties": {
"answered_by": {
"type": "string",
"enum": ["human", "ivr", "voicemail", "unknown"],
"description": "Classify the final endpoint. If an IVR transfers the call to a person, use human."
}
},
"additionalProperties": false
}Send that and the ending stops being a guess. Without it the honest answer to "did a person pick up" is that nothing in the payload establishes one, which is true and not much use to anybody.
So the first thing this skill does with a call it cannot resolve is name the field that would resolve it. A check that only ever says no gets switched off.
Note what answered_by is not. It is the platform's classification of what it
heard, so it can be wrong. What changes is who is doing the guessing: with the
field declared the claim is stated in the payload and can be pointed at, instead
of being inferred by whatever read it.
The four things it reconciles
Each one is a state somebody has reported and nothing has closed.
Nobody is watching it. The call is still open, and long enough has passed that whatever was waiting has already given up. A client timeout is not the same as the call ending, and a call can dial well after the SDK has raised.
It may have gone out twice. The returned call is older than the request that returned it, so the platform handed back one that already existed. A replay otherwise reads exactly like a fresh creation.
The clock contradicts itself. An attempt that claims to have run longer than the call existed, or one timestamped outside the window the events describe. Only contradictions count. An event stream wider than the attempt window is normal, because the stream also covers queuing and finalization.
The retry is not safe. The submission is in an unknown state, or the same idempotency key was refused after a failure. Deriving the key from the authorization rather than the attempt is what makes the next attempt answerable: same approved action, same key, so a retry cannot become a second call.
Show full SKILL.md (232 more words)Show less
Read the event stream, not the attempt clock
GET /v1/calls/{call_id}/events carries a created_at on every event, declared
format: date-time, and those timestamps hold still.
The attempt timestamps do not. On a finished call they can be rewritten shortly after it settles: the offset is dropped, the value moves, and sub-second precision is lost to rounding. Read the same call twice and you can get two different answers about how long it ran. A sub-second attempt rounds to zero.
So reconstruct timing from events and treat the attempt fields as evidence about
the attempt rather than as a clock. references/observed-shapes.md shows the
shape with invented values and how to check it on your own account.
What it will not do
It reads fields. It does not interpret a transcript, score anything, or ask a model what it thinks, so every sentence it produces traces to a value in the payload and says the same thing every time.
It never resolves the business outcome. Where a reading rests on inference it is marked as inference and routed to a person, and where no field carries the fact at all it says that rather than filling the gap.
It places no calls.
References
references/observed-shapes.md- the platform behaviours this relies on, with invented values, and how to check each one yourself.references/reading-a-call.md- the three axes, the endings each surface can and cannot express, and worked examples.
© CALLE-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (references) in skills/call-state-reconciler of CALLE-AI/awesome-phone-call-agents.
- SKILL.md
- references/examples.md
- references/observed-shapes.md
- references/reading-a-call.md
- references/safety.md
Open the folder on GitHubat commit 38d4118
Compare with similar skills
Call State Reconciler next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Call State Reconciler this skillCALLE-AI/awesome-phone-call-agents | 107 | — | ~1.4k | Automated safety check: Pass | MIT | |
| ActualizeNeoLabHQ/context-engineering-kit | 1.8k | — | ~932 | Automated safety check: Pass | GPL-3.0 | |
| Reconciling Problem Listsmaziyarpanahi/openmed | 5.5k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Is This Actually Goodmohitagw15856/pm-claude-skills | 1.4k | — | ~884 | Automated safety check: Pass | MIT | |
| Attribution Reconcileraaron-he-zhu/aaron-marketing-skills | 2.9k | 2 repos | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Actual Budgetsundial-org/awesome-openclaw-skills | 663 | — | ~1.6k | Automated safety check: Pass | None |
Similar skills
Reconciling Problem Lists
maziyarpanahi/openmed
Deduplicate and reconcile OpenMed-extracted conditions into one clean active problem list with clinical status (active / resolved / historical).
Is This Actually Good
mohitagw15856/pm-claude-skills
Get an honest verdict on whether something you made is actually good — not the reflexive 'this is great!' but a real, criteria-based judgment.
Attribution Reconciler
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly)…
Actual Budget
sundial-org/awesome-openclaw-skills
Query and manage personal finances via the official Actual Budget Node.js API.
Netbox Reconcile
automateyournetwork/netclaw
Reconcile NetBox source of truth against live network state - detect IP drift, missing interfaces, undocumented links, cable mismatches, VLAN mismatches, and ticket discrepancies in ServiceNow.
More from CALLE-AI/awesome-phone-call-agents
All 101 skills in this repoAccessible Outing Verifier
CALLE-AI/awesome-phone-call-agents
Demonstrates advisory accessibility-planning checks with offline fixtures and a proposed bounded CALL-E workflow; use for exploring unknown or qualified venue claims without making calls.
Ground Truth Gate
CALLE-AI/awesome-phone-call-agents
A skill your agent uses when an agent holds some evidence for a physical-world claim but the evidence is broader, narrower, or older than the exact question asked, and it must first decide whether a…
Is It Accessible
CALLE-AI/awesome-phone-call-agents
Call a venue and ask the accessibility questions that matter to one specific person — step-free entry, hearing loop, guide dogs, quiet hours, changing places — then return a per-need verdict backed…
Landmark Navigation Assist
CALLE-AI/awesome-phone-call-agents
Turns a pre-written, building-level location config into a CALL-E outbound phone-call task that guides a delivery driver through the last few hundred metres to a specific building using landmarks…
Research Gap Call Verifier
CALLE-AI/awesome-phone-call-agents
Turn cited business research into a bounded, approval-gated phone-call plan that asks only unresolved factual questions, then reconcile CALL-E-compatible results without treating voicemail, refusal…
Structured Outcome Followup Call
CALLE-AI/awesome-phone-call-agents
Place a goal-driven CALL-E call that collects specific structured answers, score those answers against a deterministic rubric you supply, and conditionally trigger a follow-up action — all runnable…
Questions about Call State Reconciler
What does Call State Reconciler do?
Work out what actually happened to a CALL-E call by reading the call task, its attempts and its event stream together, and say which field each conclusion came from. Call State Reconciler is an agent skill from CALLE-AI/awesome-phone-call-agents. Work out what actually happened to a CALL-E call by reading the call task, its attempts and its event stream together, and say which field each conclusion came from.
When should I use Call State Reconciler?
Call State Reconciler fits situations like: A workflow acts on a call result; A call will not settle; the platforms own signals disagree with each other.
How do I install Call State Reconciler in Claude Code?
Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a claude-code`. Or copy the skill folder (skills/call-state-reconciler in CALLE-AI/awesome-phone-call-agents) into .claude/skills/call-state-reconciler in your project. Claude Code loads it when a task matches its description.
How do I install Call State Reconciler in Codex?
Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a codex`. Or copy the skill folder (skills/call-state-reconciler in CALLE-AI/awesome-phone-call-agents) into .agents/skills/call-state-reconciler in your project. Codex loads it when a task matches its description.
Can I use Call State Reconciler in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CALLE-AI/awesome-phone-call-agents --skill call-state-reconciler -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/call-state-reconciler, .gemini/skills/call-state-reconciler, .github/skills/call-state-reconciler and .opencode/skills/call-state-reconciler in your project.
What does Call State Reconciler need to run?
SKILL.md names no scripts, command-line tools or credentials: Call State Reconciler is instructions for the agent only.
Does Call State Reconciler access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Call State Reconciler safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Call State Reconciler use?
Call State Reconciler is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Call State Reconciler use?
About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.5k tokens, read only when the agent opens those files.
What are the alternatives to Call State Reconciler?
Skills that share tags, products or a category with Call State Reconciler: Actualize (NeoLabHQ/context-engineering-kit, 1.8k stars), Reconciling Problem Lists (maziyarpanahi/openmed, 5.5k stars), Is This Actually Good (mohitagw15856/pm-claude-skills, 1.4k stars) and Attribution Reconciler (aaron-he-zhu/aaron-marketing-skills, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Call State Reconciler?
CALLE-AI (a GitHub organization) maintains it in CALLE-AI/awesome-phone-call-agents, which has 107 GitHub stars. The repository holds 101 skills in this directory. The repository was last updated on October 10, 2026.
Source: CALLE-AI/awesome-phone-call-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.