No. Slack Web API returns a success response when it accepts the request. The message then holds one of 3 states. Only bot_message is terminal success. Provely proves posted_to_user and posted as separate promises.
| Fact | Value |
|---|---|
| Skill version | 0.1.0 |
| Publisher | Built and signed by Provely. |
| Certification | Provisional (score 49 of 100) |
| Last conformance run | 2026-09-05T12:00:00Z: 26 of 26 cases passed, 0 critical false VERIFIED |
| Provider API versions | fp_2026_09 |
| Default provider API version | fp_2026_09 |
| Compiled | 2026-09-05T12:00:00Z by compiler 0.1.0 |
| Manifest hash | 79be37dad2c03c4f |
| Manifest hash check | the document hashes to the value the manifest states |
| Signature | valid, key provely-skill-2026-09, trusted by this build |
What does this page prove?
| Claim | Proven by | Evidence | Status |
|---|---|---|---|
| The post event states the channel_type im, so the message reached a direct message conversation and not a public channel. It does not prove which person. | slack.direct_message.posted | E2 + E3 | proven |
| The conversation holds one message with the intended text at the ts that Slack returned. It does not prove that a person read the message. | slack.message.posted | E2 + E3 | proven |
| An outcome outside Slack Web API, such as a bank credit or a person who read a message | not proven | no E5 channel | not proven |
| The agent report that the action worked | never counts | E0 | not proven |
Which completion levels does the Slack Web API skill expose?
Each level is one promise with one contract. An agent picks the level that matches the promise it makes. It cannot upgrade a level. Read the completion level definition.
| Level | Contract | Promise | Evidence | Certification |
|---|---|---|---|---|
posted_to_user | slack.direct_message.posted v1.0.0 | The post event states the channel_type im, so the message reached a direct message conversation and not a public channel. It does not prove which person. | E2 + E3 | Provisional |
posted | slack.message.posted v1.0.0 | The conversation holds one message with the intended text at the ts that Slack returned. It does not prove that a person read the message. | E2 + E3 | Provisional |
What is the Slack Web API lifecycle?
Which states can a slack.message be in?
| State | Class | Verdict | Meaning | Source |
|---|---|---|---|---|
bot_message | terminal success | VERIFIED | An integration posted the message, and Slack holds it in the conversation. The subtype table states that bot_message means a message that an integration posted. | slack.openapi |
message_changed | terminal neutral | FAILED | A person or an app changed the message. The record is hidden, so conversations.history returns it no longer. | slack.openapi |
message_deleted | terminal neutral | FAILED | A person or an app deleted the message. The record is hidden, so conversations.history returns it no longer. | slack.openapi |
In slack.message under provider API version fp_2026_09, bot_message is the only state that means terminal success. Every other state gives PENDING, FAILED, or UNVERIFIABLE.
Source: slack.openapi · retrieved 2026-09-08
How does Provely tie the evidence to this exact operation?
A matching state that already existed must not verify. Every contract names the correlation keys that bind the evidence to the operation, and the idempotency key that stops a duplicate side effect.
| Strategy | Assurance | Keys | Required | Window |
|---|---|---|---|---|
resource_id | strong | message_ts from $action.result.ts | yes | none |
fingerprint | weak | channel from $input.channel_id; text from $input.text | no | 600000 ms |
In words
- E0 agent assertion: never sufficient.
- E1 action response: the provider acknowledged the request.
- E2 provider readback: the runtime read the resource back.
- E3 provider event: the provider reported the change.
- E4 independent system: a system outside the action path agrees.
- E5 external outcome: the result is observable in the world.
Which evidence channels does the skill read?
The runtime prefers the channel that is more independent from the action path. Read the evidence level definition. An acknowledgement from Slack Web API is E1 and never terminal success.
| Channel | Level | Independence | Verifier | Deterministic | Typical latency |
|---|---|---|---|---|---|
direct_message_posted_event | E3 | provider event | webhook | no | 2000 ms |
message_action_response | E1 | same response | action_result | yes | not stated |
message_conversation_posts | E3 | provider event | webhook | no | 2000 ms |
message_posted_event | E3 | provider event | webhook | no | 2000 ms |
message_readback | E2 | provider readback | http | yes | 300 ms |
Which ways can a Slack Web API action look done and not be?
| Contract | Case | Rule | Verdict |
|---|---|---|---|
| slack.direct_message.posted | wrong subject | Slack holds a different text than the intent stated. Ask a person. | CONTRADICTED |
| slack.direct_message.posted | pre existing state | The message is older than the operation. It proves nothing. | CONTRADICTED |
| slack.direct_message.posted | duplicate side effect | Slack holds more than one message of this text in this conversation since the operation started. Do not retry. | CONTRADICTED |
| slack.direct_message.posted | observed state | Slack answered the read with the status code 200 and the member ok false. The answer is a refusal and it is no evidence. | UNVERIFIABLE |
| slack.message.posted | wrong subject | Slack holds a different text than the intent stated. Ask a person. | CONTRADICTED |
| slack.message.posted | pre existing state | The message is older than the operation. It proves nothing. | CONTRADICTED |
| slack.message.posted | duplicate side effect | Slack holds more than one message of this text in this conversation since the operation started. Do not retry. | CONTRADICTED |
| slack.message.posted | observed state | Slack answered the read with the status code 200 and the member ok false. The answer is a refusal and it is no evidence. | UNVERIFIABLE |
What did the last conformance run show?
| Dimension | Score | Maximum |
|---|---|---|
| Documentation | 14 | 20 |
| Schema alignment | 12.27 | 15 |
| Lifecycle certainty | 20 | 20 |
| Evidence strength | 16 | 20 |
| Causal correlation | 15 | 15 |
| Sandbox conformance | 10 | 10 |
| Raw score | 87.27 | 100 |
| Score after the caps | 49 | 100 |
The raw score is 87.27. 2 hard caps apply, so the score is 49 and the level is Provisional.
| Reason | Highest score it allows |
|---|---|
| 8 uncertainty records are open. The lowest cap is 49. | 49 |
| 2 mandatory cases are missing. Example: slack.direct_message.posted:terminal_failure. | 74 |
| Contract | Raw score | Score after the caps | Certification |
|---|---|---|---|
slack.direct_message.posted | 87.27 | 49 | Provisional |
slack.message.posted | 87.27 | 49 | Provisional |
The weakest contract is slack.direct_message.posted. It scores 49 and reaches Provisional. The package level is Provisional, because a package level never rises above its weakest contract. Read the level of the contract you use.
The last conformance run on 2026-09-05T12:00:00Z passed 26 of 26 cases with 0 critical false VERIFIED. One critical false VERIFIED rejects a skill.
| Case class | Passed | Total |
|---|---|---|
| duplicate side effect | 2 | 2 |
| error after execution | 2 | 2 |
| error before execution | 2 | 2 |
| evidence unavailable | 2 | 2 |
| pre existing state | 2 | 2 |
| stale readback | 2 | 2 |
| still transitional | 2 | 2 |
| terminal success | 2 | 2 |
| timeout after commit | 2 | 2 |
| version mismatch | 2 | 2 |
| webhook duplicate | 2 | 2 |
| webhook out of order | 2 | 2 |
| wrong subject | 2 | 2 |
The conformance artifact digest is 93b0aad442916550. The harness signs the run, so a reader can check that these numbers come from that run.
What remains uncertain?
The level is Provisional because of it. 8 uncertainty records are open. The lowest cap is 49. Provely does not guess a rule that a source does not state.
Where do these facts come from?
Every claim above cites a source assertion in the skill provenance. The compiler records the source, its hash, and the retrieval date. A page never states a provider rule without one.
| Source | Kind | Retrieved | Excerpt |
|---|---|---|---|
| slack.docs.conversations | docs | 2026-09-08 | authored |
| slack.docs.events | docs | 2026-09-08 | authored |
| slack.docs.post_message | docs | 2026-09-08 | authored |
| slack.docs.web_api | docs | 2026-09-08 | authored |
| slack.events | event sample | 2026-09-08 | authored |
| slack.openapi | openapi | 2026-09-08 | authored |
How do I verify a Slack Web API action?
Verify a Slack Web API action with Provely
- Begin the operation.Call
beginwith the contractslack.direct_message.postedand the input. Keep the operation id. - Make the Slack Web API call you make today.Send the request with the correlation metadata that
beginreturned. - Submit the acknowledgement.Call
action_resultwith the Slack Web API response. This is evidence level E1. It is not completion. - Verify.Call
verify. The runtime readsdirect_message_posted_event,message_action_response,message_conversation_posts,message_posted_eventandmessage_readbackand evaluates the contract. - Report the verdict exactly as returned.VERIFIED comes with a signed receipt. PENDING comes with the operation id. CONTRADICTED and UNVERIFIABLE are not success.
Questions developers ask
Does the posted_to_user level prove the posted level?
No. The post event states the channel_type im, so the message reached a direct message conversation and not a public channel. It does not prove which person. The conversation holds one message with the intended text at the ts that Slack returned. It does not prove that a person read the message. Use slack.message.posted to prove posted.
Which Slack Web API API versions does the skill support?
fp_2026_09. An operation on another version returns UNVERIFIABLE with the reason version_unsupported. The runtime never guesses.
Does Provely need write access to Slack Web API?
No. The agent keeps its write key. The verifier reads with a separate read-only credential where Slack Web API permits it, and it never shares that credential with the agent.